Detection of Underwater Marine Plastic Debris Using an Augmented Low Sample Size Dataset for Machine Vision System: A Deep Transfer Learning Approach

被引：10

作者：

Hipolito, Japhet C. ^{[1
]}

Alon, Alvin Sarraga ^{[2
]}

Amorado, Ryndel, V ^{[1
]}

Fernando, Maricel Grace Z. ^{[1
]}

De Chavez, Poul Isaac C. ^{[1
]}

机构：

[1] Batangas State Univ, Coll Informat & Comp Sci, Batangas City, Philippines

[2] Batangas State Univ, STEER Hub, Digital Transformat Ctr, Batangas City, Philippines

来源：

19TH IEEE STUDENT CONFERENCE ON RESEARCH AND DEVELOPMENT (SCORED 2021) | 2021年

关键词：

object detection; deep learning; transfer learning; marine plastic waste detection; yolov3;

D O I：

10.1109/SCOReD53546.2021.9652703

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Waste in aquatic environments devastates aquatic habitats and offers a tall environmental and economical risk. Machine Vision might play a role in resolving this issue by detecting and finally eliminating debris. Using an augmented low sample size from a publicly available collection of underwater plastic waste, this research employed a YOLOv3 deep-learning system to visually recognize debris in realistic underwater environments. The detection model has a training and validation accuracy of 98.026 % and 94.582 %, respectively, according to the study's findings, with an mAP value of 98.15%. With its effectiveness in detecting underwater plastic waste, the recommended model is suitable for a variety of machine vision systems. The system has a 100% testing accuracy, with detection per frame accuracy ranging from 60.59% to 98.89%.

引用

页码：82 / 86

页数：5

共 29 条

[1] Abdel-shafy HI., 2018, J. Pet., V27, P1275, DOI [10.1016/j.ejpe.2018.07.003, DOI 10.1016/J.EJPE.2018.07.003]
[2] Alon H., 2021, 2021 INT C COMP INT, DOI [10.1109/ iccike51210.2021.9410803, DOI 10.1109/ICCIKE51210.2021.9410803]
[3] Alon H., 2020, 2020 IEEE 7 INT C EN, DOI [10.1109/ icetas51660.2020.9484315, DOI 10.1109/ICETAS51660.2020.9484315]
[4] Coordination and harmonization of a marine plastic debris monitoring program for beaches in the Wider Caribbean Region: Identifying strategic pathways forward
Ambrose, Kristal K.
[J]. MARINE POLLUTION BULLETIN, 2021, 171
[5] Occurrence and abundance of meso and microplastics in sediment, surface waters, and marine biota from the South Pacific region
Bakir, Adil
Desender, Marieke
Wilkinson, Tim
Van Hoytema, Nanne
Amos, Ruth
Airahui, Sammy
Graham, Jennifer
Maes, Thomas
[J]. MARINE POLLUTION BULLETIN, 2020, 160 (160)
[6] Plastics in marine ecosystem: A review of their sources and pollution conduits
Bhuyan, Md. Simul
Venkatramanan, S.
Selvam, S.
Szabo, Sylvia
Hossain, Md. Maruf
Rashed-Un-Nabi, Md.
Paramasivam, C. R.
Jonathan, M. P.
Islam, Md. Shafiqul
[J]. REGIONAL STUDIES IN MARINE SCIENCE, 2021, 41
[7] Effects of ocean sprawl on ecological connectivity: impacts and solutions
Bishop, Melanie J.
Mayer-Pinto, Mariana
Airoldi, Laura
Firth, Louise B.
Morris, Rebecca L.
Loke, Lynette H. L.
Hawkins, Stephen J.
Naylor, Larissa A.
Coleman, Ross A.
Chee, Su Yin
Dafforn, Katherine A.
[J]. JOURNAL OF EXPERIMENTAL MARINE BIOLOGY AND ECOLOGY, 2017, 492 : 7 - 30
[8] Bugeja M., 2020, TRANSPORTATION RES P, V45, P971, DOI [10.1016/j.trpro.2020.02.069, DOI 10.1016/J.TRPRO.2020.02.069]
[9] Selective feature connection mechanism: Concatenating multi-layer CNN features with a feature selector
Du, Chen
Wang, Chunheng
Wang, Yanna
Shi, Cunzhao
Xiao, Baihua
[J]. PATTERN RECOGNITION LETTERS, 2020, 129 : 108 - 114
[10] Distribution of plastic polymer types in the marine environment; A meta-analysis
Erni-Cassola, Gabriel
Zadjelovic, Vinko
Gibson, Matthew I.
Christie-Oleza, Joseph A.
[J]. JOURNAL OF HAZARDOUS MATERIALS, 2019, 369 : 691 - 698

← 1 2 3 →