Redirigiendo al acceso original de articulo en 21 segundos...
Inicio  /  Drones  /  Vol: 5 Par: 1 (2021)  /  Artículo
ARTÍCULO
TITULO

A Citizen Science Unmanned Aerial System Data Acquisition Protocol and Deep Learning Techniques for the Automatic Detection and Mapping of Marine Litter Concentrations in the Coastal Zone

Apostolos Papakonstantinou    
Marios Batsaris    
Spyros Spondylidis and Konstantinos Topouzelis    

Resumen

Marine litter (ML) accumulation in the coastal zone has been recognized as a major problem in our time, as it can dramatically affect the environment, marine ecosystems, and coastal communities. Existing monitoring methods fail to respond to the spatiotemporal changes and dynamics of ML concentrations. Recent works showed that unmanned aerial systems (UAS), along with computer vision methods, provide a feasible alternative for ML monitoring. In this context, we proposed a citizen science UAS data acquisition and annotation protocol combined with deep learning techniques for the automatic detection and mapping of ML concentrations in the coastal zone. Five convolutional neural networks (CNNs) were trained to classify UAS image tiles into two classes: (a) litter and (b) no litter. Testing the CCNs? generalization ability to an unseen dataset, we found that the VVG19 CNN returned an overall accuracy of 77.6% and an f-score of 77.42%. ML density maps were created using the automated classification results. They were compared with those produced by a manual screening classification proving our approach?s geographical transferability to new and unknown beaches. Although ML recognition is still a challenging task, this study provides evidence about the feasibility of using a citizen science UAS-based monitoring method in combination with deep learning techniques for the quantification of the ML load in the coastal zone using density maps.

 Artículos similares

       
 
Guido Salazar-Sepúlveda, Alejandro Vega-Muñoz, Nicolás Contreras-Barraza, Dante Castillo, Mario Torres-Alcayaga and Carolina Cornejo-Orellana    
The aim of this study is to present an overview of the current scientific literature pertaining to ocean literacy. We applied a bibliometric method to examine relational patterns among publications in a set of 192 papers indexed from 2004 to 2023 in Web ... ver más
Revista: Water

 
Jason Corburn, Patrick Njoroge, Jane Weru and Maureen Musya    
Urban informal settlements or slums are among the most vulnerable places to climate-change-related health risks. Yet, little data exist documenting environmental and human health vulnerabilities in slums or how to move research to action. Citizen science... ver más
Revista: Urban Science

 
Stephanie Pyne, Melissa Castron, Annita Parish, Peter Farrell and Shawn Johnston    
Joseph Kerski has identified five converging global trends?geo-awareness, geo-enablement, geotechnologies, citizen science, and storytelling?which contribute to the increased relevance of geography for education and society. While these trends are discus... ver más

 
Joshua Randall, Nicole C. Inglis, Lindsey Smart and Jelena Vukomanovic    
Invasive species are an important and growing issue of concern for land managers, and the ability to collect and visualize species coverage data is vital to the management of invasive and native species. This is particularly true of spatial data, which p... ver más

 
Laurissa C. Heidkamp and Alan D. Christian    
Land use land cover within a watershed influences stream water quality, habitat quality, and biological community structure. As development and associated impervious surface increases in a watershed, changes in storm water and nutrient inputs generally c... ver más
Revista: Urban Science