A deep learning approach for detecting underwater plastic waste

M. Delina; P.F. Akbar; A.M. Hussaan; A.F. Harlastputra; D.S.S.P. Anugrah; P. Renaldi; D. Noviarini

doi:10.1088/1742-6596/2596/1/012027

← Back to search

A deep learning approach for detecting underwater plastic waste

Open

M. Delina, P.F. Akbar, A.M. Hussaan, A.F. Harlastputra, D.S.S.P. Anugrah, P. Renaldi, D. Noviarini

2023 Journal of Physics: Conference Series Vol. 2596 Issue 1 Conference paper Cited by 7 SDG 17SDG 6SDG 12

Abstract

The water pollution, flooding, and recycling issues in Indonesia are exacerbated by the critical level of underwater plastic waste. Furthermore, the lack of visibility makes it difficult to collect plastic waste in the water. In this research, a plastic detection instrument was developed to detect water pollution using a deep learning method with the You Only Look Once version 3 (YOLOv3) algorithm. The study was conducted in four steps: 1) create a custom dataset of plastic waste images, 2) annotated the plastic waste dataset, 3) configurated and train the model, 4) validated the result. The proposed model has achieved an overall mean average precision (mAP) of 83.12% This result indicated that the model is effective in detecting plastic waste in underwater environment. © Published under licence by IOP Publishing Ltd.

Affiliations

Department of Physics, Universitas Negeri Jakarta, Jl. Rawamangun Muka, Jakarta, 13220, Indonesia; Department of Computer Science, Iqra University, Rd. Shaheed-e-Millat, Sindh, 75500, Pakistan; Faculty of Economics, Universitas Negeri Jakarta, Jl. Rawamangun Muka, Jakarta, 13220, Indonesia

View full text (DOI) →

Research at a Glance

Research at a Glance

Topics & SDG Alignment

Collaboration

Author Profile (Selected)

References Overview

Journal & Source

Metadata & Integrity