EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning-based image classification of sea turtles using object detection and instance segmentation models

Jong-Won Baek, Jung-Il Kim, Chang-Bae Kim iD

PLOS ONE · 25.11.2024 · 19 (11) · e0313323

DOI: 10.1371/journal.pone.0313323 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 25.11.2024. Verfasst von Jong-Won Baek und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biotechnology, Sangmyung University, Seoul, Korea. Hauptthemen laut MEDLINE: Turtles, Deep Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute of Biological Resources.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sea turtles exhibit high migratory rates and occupy a broad range of habitats, which in turn makes monitoring these taxa challenging. Applying deep learning (DL) models to vast image datasets collected from citizen science programs can offer promising solutions to overcome the challenge of monitoring the wide habitats of wildlife, particularly sea turtles. Among DL models, object detection models, such as the You Only Look Once (YOLO) series, have been extensively employed for wildlife classification. Despite their successful application in this domain, detecting objects in images with complex backgrounds, including underwater environments, remains a significant challenge. Recently, instance segmentation models have been developed to address this issue by providing more accurate classification of complex images compared to traditional object detection models. This study compared the performance of two state-of-the-art DL methods namely; the object detection model (YOLOv5) and instance segmentation model (YOLOv5-seg), to detect and classify sea turtles. The images were collected from iNaturalist and Google and then divided into 64% for training, 16% for validation, and 20% for test sets. Model performance during and after finishing training was evaluated by loss functions and various indexes, respectively. Based on loss functions, YOLOv5-seg demonstrated a lower error rate in detecting rather than classifying sea turtles than the YOLOv5. According to mean Average Precision (mAP) values, which reflect precision and recall, the YOLOv5-seg model showed superior performance than YOLOv5. The mAP0.5 and mAP0.5:0.95 for the YOLOv5 model were 0.885 and 0.795, respectively, whereas for the YOLOv5-seg, these values were 0.918 and 0.831, respectively. In particular, based on the loss functions and classification results, the YOLOv5-seg showed improved performance for detecting rather than classifying sea turtles compared to the YOLOv5. The results of this study may help improve sea turtle monitoring in the future.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TurtlesDeep LearningImage Processing, Computer-AssistedAnimalsEcosystem

Autor:innen und Institutionen

  • Department of Biotechnology, Sangmyung University, Seoul, Korea.

ORCID-Profile: Chang-Bae Kim

Förderung

  • National Institute of Biological Resources

Zitieren

APA

Baek, J. W., Kim, J. I., & Kim, C. B. (2024). Deep learning-based image classification of sea turtles using object detection and instance segmentation models. PLOS ONE, 19(11), e0313323. https://doi.org/10.1371/journal.pone.0313323

Vancouver

Baek JW, Kim JI, Kim CB. Deep learning-based image classification of sea turtles using object detection and instance segmentation models. PLOS ONE. 2024;19(11):e0313323. doi:10.1371/journal.pone.0313323

BibTeX
@article{Baek2024,
  author = {Baek, Jong-Won and Kim, Jung-Il and Kim, Chang-Bae},
  title = {Deep learning-based image classification of sea turtles using object detection and instance segmentation models},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {11},
  pages = {e0313323},
  doi = {10.1371/journal.pone.0313323}
}
Kostenlos starten →