Deep learning-based software for detecting population density of Antarctic birds
Monitoring populations of bird species living in Antarctica with current technologies is critical to the future of habitats on the continent. Studies of bird species living in Antarctica are limited due to climate, challenging geographic conditions, and transportation and logistical constraints. The...
Published in: | Computer Science Journal of Moldova |
---|---|
Main Author: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Vladimir Andrunachievici Institute of Mathematics and Computer Science
2023
|
Subjects: | |
Online Access: | https://doi.org/10.56415/csjm.v31.11 https://doaj.org/article/2c6f5900e3db42869a7a7a9a4f9cb12d |
id |
ftdoajarticles:oai:doaj.org/article:2c6f5900e3db42869a7a7a9a4f9cb12d |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:2c6f5900e3db42869a7a7a9a4f9cb12d 2023-09-05T13:13:39+02:00 Deep learning-based software for detecting population density of Antarctic birds Sinan Uğuz 2023-07-01T00:00:00Z https://doi.org/10.56415/csjm.v31.11 https://doaj.org/article/2c6f5900e3db42869a7a7a9a4f9cb12d EN eng Vladimir Andrunachievici Institute of Mathematics and Computer Science http://www.math.md/files/csjm/v31-n2/v31-n2-(pp200-216).pdf https://doaj.org/toc/1561-4042 https://doaj.org/toc/2587-4330 https://doi.org/10.56415/csjm.v31.11 1561-4042 2587-4330 https://doaj.org/article/2c6f5900e3db42869a7a7a9a4f9cb12d Computer Science Journal of Moldova, Vol 31, Iss 2(92), Pp 200-216 (2023) deep learning antarctic birds remote sensing population estimation convolutional neural network Electronic computers. Computer science QA75.5-76.95 article 2023 ftdoajarticles https://doi.org/10.56415/csjm.v31.11 2023-08-13T00:36:40Z Monitoring populations of bird species living in Antarctica with current technologies is critical to the future of habitats on the continent. Studies of bird species living in Antarctica are limited due to climate, challenging geographic conditions, and transportation and logistical constraints. The goal of this study is to develop Deep Learning-based software to determine the population densities of Antarctic penguins and endangered albatrosses. Images of penguins and albatrosses obtained from internet sources were labeled using the segmentation technique. For this purpose, 4144 labeled data were trained with five different convolutional neural network architectures TOOD, YOLOv3, YOLOF, Mask R-CNN, and Sparse R-CNN. The performance of the obtained models was measured using the average precision (AP) metric. The experimental results show that the TOOD-ResNet50 model with 0.73 {$AP^{50}$} detects the Antarctic birds adequately compared to the other models. At the end of the study, a software was developed to detect penguins and albatrosses in real time. Article in Journal/Newspaper Antarc* Antarctic Antarctica Directory of Open Access Journals: DOAJ Articles Antarctic The Antarctic Computer Science Journal of Moldova 31 2 (92) 200 216 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
deep learning antarctic birds remote sensing population estimation convolutional neural network Electronic computers. Computer science QA75.5-76.95 |
spellingShingle |
deep learning antarctic birds remote sensing population estimation convolutional neural network Electronic computers. Computer science QA75.5-76.95 Sinan Uğuz Deep learning-based software for detecting population density of Antarctic birds |
topic_facet |
deep learning antarctic birds remote sensing population estimation convolutional neural network Electronic computers. Computer science QA75.5-76.95 |
description |
Monitoring populations of bird species living in Antarctica with current technologies is critical to the future of habitats on the continent. Studies of bird species living in Antarctica are limited due to climate, challenging geographic conditions, and transportation and logistical constraints. The goal of this study is to develop Deep Learning-based software to determine the population densities of Antarctic penguins and endangered albatrosses. Images of penguins and albatrosses obtained from internet sources were labeled using the segmentation technique. For this purpose, 4144 labeled data were trained with five different convolutional neural network architectures TOOD, YOLOv3, YOLOF, Mask R-CNN, and Sparse R-CNN. The performance of the obtained models was measured using the average precision (AP) metric. The experimental results show that the TOOD-ResNet50 model with 0.73 {$AP^{50}$} detects the Antarctic birds adequately compared to the other models. At the end of the study, a software was developed to detect penguins and albatrosses in real time. |
format |
Article in Journal/Newspaper |
author |
Sinan Uğuz |
author_facet |
Sinan Uğuz |
author_sort |
Sinan Uğuz |
title |
Deep learning-based software for detecting population density of Antarctic birds |
title_short |
Deep learning-based software for detecting population density of Antarctic birds |
title_full |
Deep learning-based software for detecting population density of Antarctic birds |
title_fullStr |
Deep learning-based software for detecting population density of Antarctic birds |
title_full_unstemmed |
Deep learning-based software for detecting population density of Antarctic birds |
title_sort |
deep learning-based software for detecting population density of antarctic birds |
publisher |
Vladimir Andrunachievici Institute of Mathematics and Computer Science |
publishDate |
2023 |
url |
https://doi.org/10.56415/csjm.v31.11 https://doaj.org/article/2c6f5900e3db42869a7a7a9a4f9cb12d |
geographic |
Antarctic The Antarctic |
geographic_facet |
Antarctic The Antarctic |
genre |
Antarc* Antarctic Antarctica |
genre_facet |
Antarc* Antarctic Antarctica |
op_source |
Computer Science Journal of Moldova, Vol 31, Iss 2(92), Pp 200-216 (2023) |
op_relation |
http://www.math.md/files/csjm/v31-n2/v31-n2-(pp200-216).pdf https://doaj.org/toc/1561-4042 https://doaj.org/toc/2587-4330 https://doi.org/10.56415/csjm.v31.11 1561-4042 2587-4330 https://doaj.org/article/2c6f5900e3db42869a7a7a9a4f9cb12d |
op_doi |
https://doi.org/10.56415/csjm.v31.11 |
container_title |
Computer Science Journal of Moldova |
container_volume |
31 |
container_issue |
2 (92) |
container_start_page |
200 |
op_container_end_page |
216 |
_version_ |
1776204855402037248 |