EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BePLi Dataset v1: Beach Plastic Litter Dataset version 1 for instance segmentation of beach plastic litter

Mitsuko Hidaka, Koshiro Murakami, Kenta Koshidawa, Shintaro Kawahara, Daisuke Sugiyama, Shin'ichiro Kako, Daisuke Matsuoka

Data in Brief · 2023-06 · 48 · 109176

DOI: 10.1016/j.dib.2023.109176 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data in Brief, 2023-06. Verfasst von Mitsuko Hidaka und 6 weiteren Autor:innen. Beteiligte Einrichtung: Research Institute for Value-Added-Information Generation (VAiG), Japan Agency for Marine-Earth Science and Technology (JAMSTEC), Kanagawa, Japan. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 4 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kagoshima University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Marine plastic pollution is a pressing global issue nowadays. To address this problem, automated image analysis techniques that can identify plastic litter are necessary for scientific research and coastal management purposes. The Beach Plastic Litter Dataset version 1 (BePLi Dataset v1) comprises 3709 original images taken in various coastal environments, along with instance-based and pixel-level annotations for all plastic litter objects visible in the images. The annotations were compiled in the Microsoft Common Objects in Context (MS COCO) format, which was partially modified from the original format. The dataset enables the development of machine-learning models for instance-level and/or pixel-wise identification of beach plastic litter. All original images in the dataset were extracted from beach litter monitoring records operated by the local government of Yamagata Prefecture in Japan. Litter images were taken in different backgrounds, such as sand beaches, rocky beaches, and tetrapods. The annotations for instance segmentation of beach plastic litter were made manually, and were given for all plastics objects, including PET bottles, containers, fishing gear, and styrene foams,all of which were categorized in a single class "plastic litter". Technologies developed using this dataset have the potential to enable further scalability for the estimation of plastic litter volume. This would help researchers, including individuals, and the the government to monitor or analyze beach litter and the corresponding pollution levels.

Schlagwörter

Stichwörter der Autor:innen

AIBeach monitoringCoastal litterDeep learningMarine plasticsObject detection

Autor:innen und Institutionen

  • Research Institute for Value-Added-Information Generation (VAiG), Japan Agency for Marine-Earth Science and Technology (JAMSTEC), Kanagawa, Japan.
  • Graduate School of Science and Engineering, Kagoshima University, Kagoshima, Japan.

Förderung

  • Kagoshima University

Zitieren

APA

Hidaka, M., Murakami, K., Koshidawa, K., Kawahara, S., Sugiyama, D., Kako, S., & Matsuoka, D. (2023). BePLi Dataset v1: Beach Plastic Litter Dataset version 1 for instance segmentation of beach plastic litter. Data in Brief, 48, 109176. https://doi.org/10.1016/j.dib.2023.109176

Vancouver

Hidaka M, Murakami K, Koshidawa K, Kawahara S, Sugiyama D, Kako S, et al. BePLi Dataset v1: Beach Plastic Litter Dataset version 1 for instance segmentation of beach plastic litter. Data in Brief. 2023;48:109176. doi:10.1016/j.dib.2023.109176

BibTeX
@article{Hidaka2023,
  author = {Hidaka, Mitsuko and Murakami, Koshiro and Koshidawa, Kenta and Kawahara, Shintaro and Sugiyama, Daisuke and Kako, Shin'ichiro and Matsuoka, Daisuke},
  title = {BePLi Dataset v1: Beach Plastic Litter Dataset version 1 for instance segmentation of beach plastic litter},
  journal = {Data in Brief},
  year = {2023},
  volume = {48},
  pages = {109176},
  doi = {10.1016/j.dib.2023.109176}
}
Kostenlos starten →