Matching individual Ladoga ringed seals across short-term image sequences
Automated wildlife reidentification has attracted increasing attention in recent years as it provides a non-invasive tool to identify and to track individual wild animals over time. In this paper, the first steps are taken towards the automatic photo-identification of the Ladoga ringed seals (Pusa h...
Published in: | Mammalian Biology |
---|---|
Main Authors: | , , , , , |
Other Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Springer Nature
2022
|
Subjects: | |
Online Access: | https://lutpub.lut.fi/handle/10024/164700 |
id |
ftlappeenranta:oai:lutpub.lut.fi:10024/164700 |
---|---|
record_format |
openpolar |
spelling |
ftlappeenranta:oai:lutpub.lut.fi:10024/164700 2023-05-15T18:03:47+02:00 Matching individual Ladoga ringed seals across short-term image sequences Nepovinnykh, Ekaterina Chelak, Ilia Lushpanov, Andrei Eerola, Tuomas Kälviäinen, Heikki Chirkova, Olga Lappeenrannan-Lahden teknillinen yliopisto LUT Lappeenranta-Lahti University of Technology LUT fi=School of Engineering Science|en=School of Engineering Science| 2022-04-08 16 fulltext 1-16 https://lutpub.lut.fi/handle/10024/164700 eng eng Springer Nature 1618-1476 1616-5047 Mammalian Biology https://link.springer.com/article/10.1007/s42991-022-00229-3 https://doi.org/10.1007/s42991-022-00229-3 Nepovinnykh, E., Chelak, I., Lushpanov, A. et al. Matching individual Ladoga ringed seals across short-term image sequences. Mamm Biol (2022). https://doi.org/10.1007/s42991-022-00229-3 https://lutpub.lut.fi/handle/10024/164700 URN:NBN:fi-fe2022091358854 CC BY 4.0 openAccess © The Author(s) 2022 CC-BY Ladoga ringed seal animal re-identification photo-identification instance segmentation convolutional neural networks article publishedVersion 2022 ftlappeenranta https://doi.org/10.1007/s42991-022-00229-3 2022-09-28T22:57:22Z Automated wildlife reidentification has attracted increasing attention in recent years as it provides a non-invasive tool to identify and to track individual wild animals over time. In this paper, the first steps are taken towards the automatic photo-identification of the Ladoga ringed seals (Pusa hispida ladogensis). A method is proposed that takes a sequence of images, each containing multiple individuals as the input, and produces cropped images of seals grouped based on one certain individual per group. The method starts by detecting each seal from the images and proceeds to matching the individual seals between the images. It is shown that high grouping accuracy can be obtained with a general-purpose image retrieval method on an image sequence taken from the same location within a relatively short period of time. Each resulting group contains multiple images of one individual with slightly different variations, for example, in pose and illumination. Utilizing these images simultaneously provides more information for the individual re-identification compared to the traditional approach, i.e., which utilizes just one image at a time. It is further demonstrated that a convolutional neural network based method can be used to extract the unique pelage patterns of the seals despite the low contrast. Finally, a method is proposed and experiments with the novel Ladoga ringed seals data are carried out to provide a proof-of-concept for the individual re-identification. Publishers version Article in Journal/Newspaper Pusa hispida ringed seal LUTPub (LUT University) Mammalian Biology 102 3 935 950 |
institution |
Open Polar |
collection |
LUTPub (LUT University) |
op_collection_id |
ftlappeenranta |
language |
English |
topic |
Ladoga ringed seal animal re-identification photo-identification instance segmentation convolutional neural networks |
spellingShingle |
Ladoga ringed seal animal re-identification photo-identification instance segmentation convolutional neural networks Nepovinnykh, Ekaterina Chelak, Ilia Lushpanov, Andrei Eerola, Tuomas Kälviäinen, Heikki Chirkova, Olga Matching individual Ladoga ringed seals across short-term image sequences |
topic_facet |
Ladoga ringed seal animal re-identification photo-identification instance segmentation convolutional neural networks |
description |
Automated wildlife reidentification has attracted increasing attention in recent years as it provides a non-invasive tool to identify and to track individual wild animals over time. In this paper, the first steps are taken towards the automatic photo-identification of the Ladoga ringed seals (Pusa hispida ladogensis). A method is proposed that takes a sequence of images, each containing multiple individuals as the input, and produces cropped images of seals grouped based on one certain individual per group. The method starts by detecting each seal from the images and proceeds to matching the individual seals between the images. It is shown that high grouping accuracy can be obtained with a general-purpose image retrieval method on an image sequence taken from the same location within a relatively short period of time. Each resulting group contains multiple images of one individual with slightly different variations, for example, in pose and illumination. Utilizing these images simultaneously provides more information for the individual re-identification compared to the traditional approach, i.e., which utilizes just one image at a time. It is further demonstrated that a convolutional neural network based method can be used to extract the unique pelage patterns of the seals despite the low contrast. Finally, a method is proposed and experiments with the novel Ladoga ringed seals data are carried out to provide a proof-of-concept for the individual re-identification. Publishers version |
author2 |
Lappeenrannan-Lahden teknillinen yliopisto LUT Lappeenranta-Lahti University of Technology LUT fi=School of Engineering Science|en=School of Engineering Science| |
format |
Article in Journal/Newspaper |
author |
Nepovinnykh, Ekaterina Chelak, Ilia Lushpanov, Andrei Eerola, Tuomas Kälviäinen, Heikki Chirkova, Olga |
author_facet |
Nepovinnykh, Ekaterina Chelak, Ilia Lushpanov, Andrei Eerola, Tuomas Kälviäinen, Heikki Chirkova, Olga |
author_sort |
Nepovinnykh, Ekaterina |
title |
Matching individual Ladoga ringed seals across short-term image sequences |
title_short |
Matching individual Ladoga ringed seals across short-term image sequences |
title_full |
Matching individual Ladoga ringed seals across short-term image sequences |
title_fullStr |
Matching individual Ladoga ringed seals across short-term image sequences |
title_full_unstemmed |
Matching individual Ladoga ringed seals across short-term image sequences |
title_sort |
matching individual ladoga ringed seals across short-term image sequences |
publisher |
Springer Nature |
publishDate |
2022 |
url |
https://lutpub.lut.fi/handle/10024/164700 |
genre |
Pusa hispida ringed seal |
genre_facet |
Pusa hispida ringed seal |
op_relation |
1618-1476 1616-5047 Mammalian Biology https://link.springer.com/article/10.1007/s42991-022-00229-3 https://doi.org/10.1007/s42991-022-00229-3 Nepovinnykh, E., Chelak, I., Lushpanov, A. et al. Matching individual Ladoga ringed seals across short-term image sequences. Mamm Biol (2022). https://doi.org/10.1007/s42991-022-00229-3 https://lutpub.lut.fi/handle/10024/164700 URN:NBN:fi-fe2022091358854 |
op_rights |
CC BY 4.0 openAccess © The Author(s) 2022 |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.1007/s42991-022-00229-3 |
container_title |
Mammalian Biology |
container_volume |
102 |
container_issue |
3 |
container_start_page |
935 |
op_container_end_page |
950 |
_version_ |
1766174795979816960 |