TY - JOUR
T1 - Deploying deep learning to estimate the abundance of marine debris from video footage
AU - Teng, Cathy
AU - Kylili, Kyriaki
AU - Hadjistassou, Constantinos
N1 - Publisher Copyright:
© 2022
PY - 2022/10
Y1 - 2022/10
N2 - The insatiable desire of society for plastic goods has led to synthetic materials becoming omnipresent in the marine environment. In attempting to address the problem of plastic pollution, we propose an image classifier based on the YOLOv5 deep learning tool that is able to classify and localize marine debris and marine life in images and video recordings. Utilizing the region of interest line and the centroid tracking counting methods, the image classifier was able to count marine debris and fish displayed in video footage. Results revealed that, with a counting accuracy of 79 %, the centroid tracking method proved more efficient thanks to its ability to trace the geometric center of the bounding box of detected marine litter. Remarkably, the proposed method achieved a mean average precision of 89.4 % when validated on nine categories of objects. Finally, its impact can be enhanced substantially if integrated into other surveying methods or applications.
AB - The insatiable desire of society for plastic goods has led to synthetic materials becoming omnipresent in the marine environment. In attempting to address the problem of plastic pollution, we propose an image classifier based on the YOLOv5 deep learning tool that is able to classify and localize marine debris and marine life in images and video recordings. Utilizing the region of interest line and the centroid tracking counting methods, the image classifier was able to count marine debris and fish displayed in video footage. Results revealed that, with a counting accuracy of 79 %, the centroid tracking method proved more efficient thanks to its ability to trace the geometric center of the bounding box of detected marine litter. Remarkably, the proposed method achieved a mean average precision of 89.4 % when validated on nine categories of objects. Finally, its impact can be enhanced substantially if integrated into other surveying methods or applications.
KW - Artificial intelligence
KW - Centroid tracking
KW - Image classification
KW - Marine pollution
KW - Plastic debris detection
KW - Region of interest
UR - http://www.scopus.com/inward/record.url?scp=85136286658&partnerID=8YFLogxK
U2 - 10.1016/j.marpolbul.2022.114049
DO - 10.1016/j.marpolbul.2022.114049
M3 - Article
C2 - 36007268
AN - SCOPUS:85136286658
SN - 0025-326X
VL - 183
JO - Marine Pollution Bulletin
JF - Marine Pollution Bulletin
M1 - 114049
ER -