Anthropogenic Marine Debris assessment with Unmanned Aerial Vehicle imagery and deep learning: A case study along the beaches of the Republic of Maldives

被引:125
作者
Fallati, L. [1 ,2 ]
Polidori, A. [3 ]
Salvatore, C. [3 ]
Saponari, L. [1 ,2 ]
Savini, A. [1 ,2 ]
Galli, P. [1 ,2 ]
机构
[1] Univ Milano Bicocca, Dept Earth & Environm Sci, Milan, Italy
[2] MaRHE Ctr, Marine Res & High Educ Ctr, Magoodhoo Island Faafu A, Maldives
[3] DeepTrace Technol SRL, Milan, Italy
关键词
Anthropogenic Marine-Debris; Unmanned Aerial Vehicles; Machine learning; Deep learning algorithms; Maldives; Beach; STRUCTURE-FROM-MOTION; PLASTIC DEBRIS; FAAFU ATOLL; LITTER; ABUNDANCE; MICROPLASTICS; ACCUMULATION; REMOTE; UAVS;
D O I
10.1016/j.scitotenv.2019.133581
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Anthropogenic Marine Debris (AMD) is one of the major environmental issues of our planet to date, and plastic accounts for 80% of total AMD. Beaches represent one of the main marine compartment where AMD accumulates, but few and scattered regional assessments are available from literature reporting quantitative estimation of AMD distributed on the shorelines. However, accessing information on the AMD accumulation rate on beaches, and the associated spatiotemporal oscillations, would be crucial to refining global estimation on the dispersal mechanisms. In our work, we address this issue by proposing an ad-hoc methodology for monitoring and automatically quantifying AMD, based on the combined use of a commercial Unmanned Aerial Vehicle (UAV) (equipped with an RGB high-resolution camera) and a deep-learning based software (i.e.: PlasticFinder). Remote areas were monitored by UAV and were inspected by operators on the ground to check and to categorise all AMD dispersed on the beach. The high-resolution images obtained from UAV allowed to visually detect a percentage of the objects on the shores higher than 87.8%, thus providing suitable images to populate training and testing datasets, as well as gold standards to evaluate the software performance. PlasticFinder reached a Sensitivity of 67%, with a Positive Predictive Value of 94%, in the automatic detection of AMD, but a limitation was found, due to reduced sunlight conditions, thus restricting to the use of the software in its present version. We, therefore, confirmed the efficiency of commercial UAVs as tools for AMD monitoring and demonstrated - for the first time - the potential of deep learning for the automatic detection and quantification of AMD. (C) 2019 Elsevier B.V. All rights reserved.
引用
收藏
页数:12
相关论文
共 65 条
[1]   Origin of marine debris is related to disposable packs of ultra-processed food [J].
Andrades, Ryan ;
Martins, Agnaldo S. ;
Fardim, Lorena M. ;
Ferreira, Juliana S. ;
Santos, Robson G. .
MARINE POLLUTION BULLETIN, 2016, 109 (01) :192-195
[2]   Microplastics in the marine environment [J].
Andrady, Anthony L. .
MARINE POLLUTION BULLETIN, 2011, 62 (08) :1596-1605
[3]   Monitoring of beach litter by automatic interpretation of unmanned aerial vehicle images using the segmentation threshold method [J].
Bao, Zhongcong ;
Sha, Jinming ;
Li, Xiaomei ;
Hanchiso, Terefe ;
Shifaw, Eshetu .
MARINE POLLUTION BULLETIN, 2018, 137 :388-398
[4]  
Barnes D.K.A., 2004, SURVEYS FROM NEGOMBO
[5]   Accumulation and fragmentation of plastic debris in global environments [J].
Barnes, David K. A. ;
Galgani, Francois ;
Thompson, Richard C. ;
Barlaz, Morton .
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES, 2009, 364 (1526) :1985-1998
[6]   Combining image processing and machine learning to identify invasive plants in high-resolution images [J].
Baron, Jackson ;
Hill, D. J. ;
Elmiligi, H. .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2018, 39 (15-16) :5099-5118
[7]   UAV-based surveying in volcano-tectonics: An example from the Iceland rift [J].
Bonali, F. L. ;
Tibaldi, A. ;
Marchese, F. ;
Fallati, L. ;
Russo, E. ;
Corselli, C. ;
Savini, A. .
JOURNAL OF STRUCTURAL GEOLOGY, 2019, 121 :46-64
[8]   COMPARISON OF COMMERCIAL STRUCTURE-FROM-MOTION PHOTOGRAMMETY SOFTWARE USED FOR UNDERWATER THREE-DIMENSIONAL MODELING OF CORAL REEF ENVIRONMENTS [J].
Burns, J. H. R. ;
Delparte, D. .
3D VIRTUAL RECONSTRUCTION AND VISUALIZATION OF COMPLEX ARCHITECTURES, 2017, 42-2 (W3) :127-131
[9]   Mapping coral reefs using consumer-grade drones and structure from motion photogrammetry techniques [J].
Casella, Elisa ;
Collin, Antoine ;
Harris, Daniel ;
Ferse, Sebastian ;
Bejarano, Sonia ;
Parravicini, Valeriano ;
Hench, James L. ;
Rovere, Alessio .
CORAL REEFS, 2017, 36 (01) :269-275
[10]  
Chollet F., 2017, DEEP LEARNING WITH P