SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43972919" target="_blank" >RIV/49777513:23520/24:43972919 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/24:00377619

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10484106" target="_blank" >https://ieeexplore.ieee.org/document/10484106</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV57701.2024.00699" target="_blank" >10.1109/WACV57701.2024.00699</a>

Jazyk výsledku

angličtina

Název v původním jazyce

SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification

Popis výsledku v původním jazyce

This paper introduces the first public large-scale, long-span dataset with sea turtle photographs captured in the wild-SeaTurtleID2022. The dataset contains 8729 photographs of 438 unique individuals collected within 13 years, making it the longest-spanned dataset for animal re-identification. Each photograph includes various annotations, e.g., identity, encounter timestamp, and body parts segmentation masks. Instead of a standard &apos;&apos;random&quot;split, the dataset allows for two realistic and ecologically motivated splits: (i) time-aware: a closed-set with training, validation, and test data from different days/years, and (ii) open-set: with new unknown individuals in test and validation sets. We show that time-aware splits are essential for benchmarking methods for re-identification, as random splits lead to performance overestimation. Furthermore, a baseline instance segmentation and re-identification performance over various body parts is provided. At last, an end-to-end system for sea turtle re-identification is proposed and evaluated. The proposed system based on Hybrid Task Cascade for head instance segmentation and ArcFace-trained feature-extractor achieved an accuracy of 86.8%.

Název v anglickém jazyce

SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification

Popis výsledku anglicky

This paper introduces the first public large-scale, long-span dataset with sea turtle photographs captured in the wild-SeaTurtleID2022. The dataset contains 8729 photographs of 438 unique individuals collected within 13 years, making it the longest-spanned dataset for animal re-identification. Each photograph includes various annotations, e.g., identity, encounter timestamp, and body parts segmentation masks. Instead of a standard &apos;&apos;random&quot;split, the dataset allows for two realistic and ecologically motivated splits: (i) time-aware: a closed-set with training, validation, and test data from different days/years, and (ii) open-set: with new unknown individuals in test and validation sets. We show that time-aware splits are essential for benchmarking methods for re-identification, as random splits lead to performance overestimation. Furthermore, a baseline instance segmentation and re-identification performance over various body parts is provided. At last, an end-to-end system for sea turtle re-identification is proposed and evaluated. The proposed system based on Hybrid Task Cascade for head instance segmentation and ArcFace-trained feature-extractor achieved an accuracy of 86.8%.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

ISBN

979-8-3503-1892-0

ISSN

2472-6737

e-ISSN

2642-9381

Počet stran výsledku

11

Strana od-do

7131-7141

Název nakladatele

Institute of Electrical and Electronics Engineers Inc.

Místo vydání

Piscataway

Místo konání akce

Waikoloa, HI, USA

Datum konání akce

3. 1. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001222964607028