Underwater Object Detection model based on YOLOv3 architecture using Deep Neural Networks
P. N. Athira, T.P. Mithun Haridas, M. H. Supriya
Abstract
While analysing the strategic areas of underwater surveillance as well as resource exploration or scrutiny, object detection plays a crucial role. The capability of analysing the objects along with extracting the inherent information emphasizes the high research value of object detection in the field of underwater as well as the low light medium. The conventional systems serving this objective utilizes traditional handcrafting algorithms and computational methodologies which is highly inefficient. This brings out the need of computer vision based systems which are basically automated and will be a learning based model. This paper aims to propose a model to automatically detect underwater object using YOLOv3 architecture with darknet framework and deep learning. This paper also explores the possibility of custom training of YOLOv3 based underwater object detection models using Fish 4 Knowledge dataset.