气候变化领域集成服务门户(CCPortal): Mapping marine litter with Unmanned Aerial Systems: A showcase comparison among manual image screening and machine learning techniques

CCPortal

DOI	10.1016/j.marpolbul.2020.111158
	Mapping marine litter with Unmanned Aerial Systems: A showcase comparison among manual image screening and machine learning techniques
	Gonçalves G.; Andriolo U.; Pinto L.; Duarte D.
发表日期	2020
ISSN	0025326X
卷号	155
英文摘要	Recent works have shown the feasibility of Unmanned Aerial Systems (UAS) for monitoring marine pollution. We provide a comparison among techniques to detect and map marine litter objects on an UAS-derived orthophoto of a sandy beach-dune system. Manual image screening technique allowed a detailed description of marine litter categories. Random forest classifier returned the best-automated detection rate (F-score 70%), while convolutional neural network performed slightly worse (F-score 60%) due to a higher number of false positive detections. We show that automatic methods allow faster and more frequent surveys, while still providing a reliable density map of the marine litter load. Image manual screening should be preferred when the characterization of marine litter type and material is required. Our analysis suggests that the use of UAS-derived orthophoto is appropriate to obtain a detailed geolocation of marine litter items, requires much less human effort and allows a wider area coverage. © 2020 Elsevier Ltd
英文关键词	Beach; Coastal pollution; Convolutional neural network; Dune; Plastic; Random forest
语种	英语
scopus关键词	Antennas; Convolutional neural networks; Decision trees; Machine learning; Unmanned aerial vehicles (UAV); Area coverages; Automated detection; Automatic method; False positive detection; Machine learning techniques; Random forest classifier; Screening techniques; Unmanned aerial systems; Marine pollution; automation; comparative study; image classification; machine learning; mapping; orthophoto; pollution monitoring; solid waste; article; classifier; convolutional neural network; human; random forest; seashore; unmanned aerial vehicle; environmental monitoring; machine learning; pollution; swimming; waste; plastic; Bathing Beaches; Environmental Monitoring; Environmental Pollution; Machine Learning; Neural Networks, Computer; Plastics; Waste Products
来源期刊	Marine Pollution Bulletin
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/149004
作者单位	University of Coimbra, Department of Mathematics, Faculty of Sciences and Technology, Coimbra, Portugal; INESC Coimbra, Department of Electrical and Computer Engineering, Coimbra, Portugal; University of Coimbra, CMUC, Department of Mathematics, Faculty of Sciences and Technology, Coimbra, Portugal
推荐引用方式 GB/T 7714	Gonçalves G.,Andriolo U.,Pinto L.,et al. Mapping marine litter with Unmanned Aerial Systems: A showcase comparison among manual image screening and machine learning techniques[J],2020,155.
APA	Gonçalves G.,Andriolo U.,Pinto L.,&Duarte D..(2020).Mapping marine litter with Unmanned Aerial Systems: A showcase comparison among manual image screening and machine learning techniques.Marine Pollution Bulletin,155.
MLA	Gonçalves G.,et al."Mapping marine litter with Unmanned Aerial Systems: A showcase comparison among manual image screening and machine learning techniques".Marine Pollution Bulletin 155(2020).