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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Adam, Lukáš, Čermák, Vojtěch, Papafitsoros, Kostas, Picek, Lukáš
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909184500432896
author Adam, Lukáš
Čermák, Vojtěch
Papafitsoros, Kostas
Picek, Lukáš
author_facet Adam, Lukáš
Čermák, Vojtěch
Papafitsoros, Kostas
Picek, Lukáš
contents This paper introduces the first public large-scale, long-span dataset with sea turtle photographs captured in the wild -- SeaTurtleID2022 (https://www.kaggle.com/datasets/wildlifedatasets/seaturtleid2022). The dataset contains 8729 photographs of 438 unique individuals collected within 13 years, making it the longest-spanned dataset for animal re-identification. All photographs include various annotations, e.g., identity, encounter timestamp, and body parts segmentation masks. Instead of standard "random" splits, the dataset allows for two realistic and ecologically motivated splits: (i) a time-aware closed-set with training, validation, and test data from different days/years, and (ii) a time-aware open-set with new unknown individuals in test and validation sets. We show that time-aware splits are essential for benchmarking re-identification methods, as random splits lead to performance overestimation. Furthermore, a baseline instance segmentation and re-identification performance over various body parts is provided. Finally, 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%.
format Preprint
id arxiv_https___arxiv_org_abs_2311_05524
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification
Adam, Lukáš
Čermák, Vojtěch
Papafitsoros, Kostas
Picek, Lukáš
Computer Vision and Pattern Recognition
This paper introduces the first public large-scale, long-span dataset with sea turtle photographs captured in the wild -- SeaTurtleID2022 (https://www.kaggle.com/datasets/wildlifedatasets/seaturtleid2022). The dataset contains 8729 photographs of 438 unique individuals collected within 13 years, making it the longest-spanned dataset for animal re-identification. All photographs include various annotations, e.g., identity, encounter timestamp, and body parts segmentation masks. Instead of standard "random" splits, the dataset allows for two realistic and ecologically motivated splits: (i) a time-aware closed-set with training, validation, and test data from different days/years, and (ii) a time-aware open-set with new unknown individuals in test and validation sets. We show that time-aware splits are essential for benchmarking re-identification methods, as random splits lead to performance overestimation. Furthermore, a baseline instance segmentation and re-identification performance over various body parts is provided. Finally, 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%.
title SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.05524