Towards Underwater Sustainability using ROV Equipped with Deep Learning System

Yi Chia Wu, Po Yen Shih, Li Perng Chen, Chia Chin Wang, Hooman Samani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Underwater pollution is a long-term environmental problem. Remotely Operated Vehicle (ROV) could promote the solution of kinds of the problem by detecting environmental problems such as rubbish. The paper suggests a system based on deep-learning algorithms that can detect rubbish underwater using ROV. We built our own dataset of three different types of underwater trash for a training model based on YOLO Neural Network architectures for object detection. In this paper we used YOLOv4. The training images from our dataset apply several filters for noise reduction and image enhancement processing to improve the accuracy of the results. In our experiment, the ROV could capture the image and stream it to the computer for analysis, enhancement, and recognition.

Original languageEnglish
Title of host publication2020 International Automatic Control Conference, CACS 2020
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISBN (Electronic)9781728171982
DOIs
Publication statusPublished - 4 Nov 2020
Event2020 International Automatic Control Conference, CACS 2020 - Hsinchu, Taiwan, Province of China
Duration: 4 Nov 20207 Nov 2020

Publication series

Name2020 International Automatic Control Conference, CACS 2020

Conference

Conference2020 International Automatic Control Conference, CACS 2020
Country/TerritoryTaiwan, Province of China
CityHsinchu
Period4/11/207/11/20

Keywords

  • Deep Learning
  • Image Enhancement
  • ROV
  • Sustainability
  • Underwater
  • YOLO

Fingerprint

Dive into the research topics of 'Towards Underwater Sustainability using ROV Equipped with Deep Learning System'. Together they form a unique fingerprint.

Cite this