Toggle Main Menu Toggle Search

Open Access padlockePrints

Deep Transfer Learning Application for Intelligent Marine Debris Detection

Lookup NU author(s): Professor Cheng Chin


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


This paper aims to evaluate the state-of-the-art object detection network; YOLOv5s (You Only Look Once version 5 small) for the detection of underwater marine debris using AUVs. The development of machine learning and AUVs for detecting marine debris is reviewed. In the paper, the YOLOv5s model is trained on a marine debris dataset using transfer learning. Several other object detection models are also trained on the same dataset for comparison. The results of the trained models are evaluated and the YOLOv5s model is deployed on an Android device to determine its suitability for real-time marine debris detection onboard AUVs. Overall, the YOLOv5s was able to achieve high accuracy scores of up to 91.2% and fast detection speeds of up to 20FPS on a Poco X3 Pro.

Publication metadata

Author(s): Chia KY, Chin CS, See S

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: EANN / EAAAI 2023 24th International Conference on Engineering Applications of Neural Networks

Year of Conference: 2023

Pages: 479-490

Print publication date: 01/06/2023

Online publication date: 07/06/2023

Acceptance date: 28/03/2023

ISSN: 1865-0929

Publisher: Springer


DOI: 10.1007/978-3-031-34204-2_39

Library holdings: Search Newcastle University Library for this item

Series Title: Communications in Computer and Information Science

ISBN: 9783031342035