Re-identification of Saimaa Ringed Seals from Image Sequences
Automatic game cameras are commonly used for monitoring wildlife as they allow to document of the activity of animals in a non-invasive manner. By utilizing a large number of cameras and identifying individual animals from the images, it is possible to, for example, estimate the population size and...
Main Authors: | , , , |
---|---|
Other Authors: | , , |
Format: | Conference Object |
Language: | English |
Published: |
Springer, Cham
2023
|
Subjects: | |
Online Access: | https://lutpub.lut.fi/handle/10024/166451 |
id |
ftlappeenranta:oai:lutpub.lut.fi:10024/166451 |
---|---|
record_format |
openpolar |
spelling |
ftlappeenranta:oai:lutpub.lut.fi:10024/166451 2024-05-19T07:47:38+00:00 Re-identification of Saimaa Ringed Seals from Image Sequences Nepovinnykh, Ekaterina Vilkman, Antti Eerola, Tuomas Kälviäinen, Heikki Lappeenrannan-Lahden teknillinen yliopisto LUT Lappeenranta-Lahti University of Technology LUT fi=School of Engineering Science|en=School of Engineering Science| 2023-04-27 14 fulltext 111-125 https://lutpub.lut.fi/handle/10024/166451 eng eng Springer, Cham Scandinavian Conference on Image Analysis SCIA 2023 Lecture Notes in Computer Science 13885 0302-9743 1611-3349 Scandinavian Conference on Image Analysis 978-3-031-31435-3 https://link.springer.com/chapter/10.1007/978-3-031-31435-3 https://doi.org/10.1007/978-3-031-31435-3_8 Nepovinnykh, E., Vilkman, A., Eerola, T., Kälviäinen, H. (2023). Re-identification of Saimaa Ringed Seals from Image Sequences. In: Gade, R., Felsberg, M., Kämäräinen, JK. (eds) Image Analysis. SCIA 2023. Lecture Notes in Computer Science, vol 13885. Springer, Cham. https://doi.org/10.1007/978-3-031-31435-3_8 https://lutpub.lut.fi/handle/10024/166451 URN:NBN:fi-fe20231017140435 fi=Kaikki oikeudet pidätetään.|en=All rights reserved.| openAccess © 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG saimaa ringed seal computer vision image processing re-identification one-to-many many-to-many conferenceObject acceptedVersion 2023 ftlappeenranta https://doi.org/10.1007/978-3-031-31435-3_8 2024-05-02T00:05:19Z Automatic game cameras are commonly used for monitoring wildlife as they allow to document of the activity of animals in a non-invasive manner. By utilizing a large number of cameras and identifying individual animals from the images, it is possible to, for example, estimate the population size and study the migration patterns of the animals. Large image volumes produced by the cameras call for automated methods for the analysis. Re-identification of animals has commonly been implemented through one-to-one matching, where images are processed individually and the best match is searched from the database of known individuals one by one. Game cameras can be configured to produce a sequence of images that allows capturing the animal from multiple angles potentially improving the re-identification accuracy. In this work, the re-identification of the endangered Saimaa ringed seal (pusa hispida saimensis) from image sequences is studied. The individual identification is realized through Saimaa ringed seal’s unique pelage pattern. The proposed one-to-many and many-to-many matching methods aggregate the pelage pattern features over the whole sequence providing better embeddings for the re-identification tasks. We show that the proposed aggregation method outperforms traditional one-to-one matching based re-identification by a large margin. Post-print / Final draft Conference Object Pusa hispida ringed seal LUTPub (LUT University) 111 125 |
institution |
Open Polar |
collection |
LUTPub (LUT University) |
op_collection_id |
ftlappeenranta |
language |
English |
topic |
saimaa ringed seal computer vision image processing re-identification one-to-many many-to-many |
spellingShingle |
saimaa ringed seal computer vision image processing re-identification one-to-many many-to-many Nepovinnykh, Ekaterina Vilkman, Antti Eerola, Tuomas Kälviäinen, Heikki Re-identification of Saimaa Ringed Seals from Image Sequences |
topic_facet |
saimaa ringed seal computer vision image processing re-identification one-to-many many-to-many |
description |
Automatic game cameras are commonly used for monitoring wildlife as they allow to document of the activity of animals in a non-invasive manner. By utilizing a large number of cameras and identifying individual animals from the images, it is possible to, for example, estimate the population size and study the migration patterns of the animals. Large image volumes produced by the cameras call for automated methods for the analysis. Re-identification of animals has commonly been implemented through one-to-one matching, where images are processed individually and the best match is searched from the database of known individuals one by one. Game cameras can be configured to produce a sequence of images that allows capturing the animal from multiple angles potentially improving the re-identification accuracy. In this work, the re-identification of the endangered Saimaa ringed seal (pusa hispida saimensis) from image sequences is studied. The individual identification is realized through Saimaa ringed seal’s unique pelage pattern. The proposed one-to-many and many-to-many matching methods aggregate the pelage pattern features over the whole sequence providing better embeddings for the re-identification tasks. We show that the proposed aggregation method outperforms traditional one-to-one matching based re-identification by a large margin. Post-print / Final draft |
author2 |
Lappeenrannan-Lahden teknillinen yliopisto LUT Lappeenranta-Lahti University of Technology LUT fi=School of Engineering Science|en=School of Engineering Science| |
format |
Conference Object |
author |
Nepovinnykh, Ekaterina Vilkman, Antti Eerola, Tuomas Kälviäinen, Heikki |
author_facet |
Nepovinnykh, Ekaterina Vilkman, Antti Eerola, Tuomas Kälviäinen, Heikki |
author_sort |
Nepovinnykh, Ekaterina |
title |
Re-identification of Saimaa Ringed Seals from Image Sequences |
title_short |
Re-identification of Saimaa Ringed Seals from Image Sequences |
title_full |
Re-identification of Saimaa Ringed Seals from Image Sequences |
title_fullStr |
Re-identification of Saimaa Ringed Seals from Image Sequences |
title_full_unstemmed |
Re-identification of Saimaa Ringed Seals from Image Sequences |
title_sort |
re-identification of saimaa ringed seals from image sequences |
publisher |
Springer, Cham |
publishDate |
2023 |
url |
https://lutpub.lut.fi/handle/10024/166451 |
genre |
Pusa hispida ringed seal |
genre_facet |
Pusa hispida ringed seal |
op_relation |
Scandinavian Conference on Image Analysis SCIA 2023 Lecture Notes in Computer Science 13885 0302-9743 1611-3349 Scandinavian Conference on Image Analysis 978-3-031-31435-3 https://link.springer.com/chapter/10.1007/978-3-031-31435-3 https://doi.org/10.1007/978-3-031-31435-3_8 Nepovinnykh, E., Vilkman, A., Eerola, T., Kälviäinen, H. (2023). Re-identification of Saimaa Ringed Seals from Image Sequences. In: Gade, R., Felsberg, M., Kämäräinen, JK. (eds) Image Analysis. SCIA 2023. Lecture Notes in Computer Science, vol 13885. Springer, Cham. https://doi.org/10.1007/978-3-031-31435-3_8 https://lutpub.lut.fi/handle/10024/166451 URN:NBN:fi-fe20231017140435 |
op_rights |
fi=Kaikki oikeudet pidätetään.|en=All rights reserved.| openAccess © 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG |
op_doi |
https://doi.org/10.1007/978-3-031-31435-3_8 |
container_start_page |
111 |
op_container_end_page |
125 |
_version_ |
1799488089366724608 |