fnctId=thesis,fnctNo=348
[2024] A Study on the Monitoring of Floating Marine Macro-Litter Using a Multi-Spectral Sensor and Classification Based on Deep Learning
- 작성자
- 권희진
- 저자
- 조영헌
- 발행사항
- 발행일
- 2024/12
- 저널명
- REMOTE SENSING
- 국문초록
- 영문초록
- 정유철:공동(제1)-내부-대학원생-부산대학교,신지선:공동(참여)-내부-연구원-부산대학교,이종석:공동(참여)-내부-대학원생-부산대학교,백지연:공동(참여)-내부-대학원생-부산대학교,Daniel Schlapfer:공동(참여)-외부-회사원-ReSe Appli,김신영:공동(참여)-내부-대학원생-부산대학교,Jin-Yong Jeong:공동(참여)-외부-책임연구원-Korea Inst,조영헌:공동(교신)-내부-교수-부산대학교
Abstract
Increasing global plastic usage has raised critical concerns regarding marine pollution. This study addresses the pressing issue of floating marine macro-litter (FMML) by developing a novel monitoring system using a multi-spectral sensor and drones along the southern coast of South Korea. Subsequently, a convolutional neural network (CNN) model was utilized to classify four distinct marine litter materials: film, fiber, fragment, and foam. Automatic atmospheric correction with the drone data atmospheric correction (DROACOR) method, which is specifically designed for currently available drone-based sensors, ensured consistent reflectance across altitudes in the FMML dataset. The CNN models exhibited promising performance, with precision, recall, and F1 score values of 0.9, 0.88, and 0.89, respectively. Furthermore, gradient-weighted class activation mapping (Grad-CAM), an object recognition technique, allowed us to interpret the classification performance. Overall, this study will shed light on successful FMML identification using multi-spectral observations for broader applications in diverse marine environments.
Keywords: floating marine macro-litter; unmanned aerial vehicle; multi-spectral sensor; atmospheric correction; reflectance retrieval; convolutional neural network
- 일반텍스트
- (RCMS)(1단계_위탁) 천리안 2B호 산출물 정확도 향상 연구
- 첨부파일