Evaluating Yolov5, Yolov6, Yolov7, and Yolov8 in underwater environment: Is there real improvement?

B Gašparović, G Mauša, J Rukavina… - 2023 8th International …, 2023 - ieeexplore.ieee.org
This paper compares several new implementations of the YOLO (You Only Look Once)
object detection algorithms in harsh underwater environments. Using a dataset collected by …

Advancements in underwater imaging through machine learning: Techniques, challenges, and applications

P Naveen - Multimedia Tools and Applications, 2024 - Springer
Underwater imaging plays a critical role in various fields such as marine biology,
environmental monitoring, underwater archaeology, and defense. However, it faces unique …

Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection

H Zheng, X Guo, G Guo, Y Cao, X Hu, P Yue - Scientific Reports, 2023 - nature.com
Submarine garbage is constantly destroying the marine ecological environment and
polluting the ocean. It is critical to use detection methods to quickly locate and identify …

Identification of Underwater Structural Bridge Damage and BIM-Based Bridge Damage Management

X Li, Q Meng, M Wei, H Sun, T Zhang, R Su - Applied Sciences, 2023 - mdpi.com
The number of bridges in operation has increased. Along with the increase in the length of
time bridges are in service, the structural safety of the bridges also decreases. Bridge …

Adaptive rule-based colour component weight assignment strategy for underwater video enhancement

JP Sonawane, MD Patil, GK Birajdar - The Imaging Science …, 2024 - Taylor & Francis
Images and videos collected in an underwater environment often have low contrast, blur,
and colour cast due to two significant sources of distortion; light scattering and absorption. In …

An Improved S-Plane Controller for High-Speed Multi-Purpose AUVs with Situational Static Loads

C Jiang, J Lv, L Wan, J Wang, B He, G Wu - Journal of Marine Science …, 2023 - mdpi.com
The classic S-plane control method combines PD structure with fuzzy control theory, with the
advantages of a simple control structure and fewer parameters to be adjusted. It has been …

Underwater image processing based on CNN applications: A review

A Noor, NI Ruhaiyem - Proceedings of the Cognitive Models and Artificial …, 2024 - dl.acm.org
In recent years, due to the natural resources contained in the vast underwater world and the
diversity of organisms present in it, including microscopic organisms, coral reefs, seaweed …

Deep learning for detection and counting of Nephrops norvegicus from underwater videos

AB Burguera, F Bonin-Font… - ICES Journal of …, 2024 - academic.oup.com
Abstract The Norway lobster (Nephrops norvegicus) is one of the most important fishery
items for the EU blue economy. This paper describes a software architecture based on …

Revealing the Potential of Deep Learning for Detecting Submarine Pipelines in Side-Scan Sonar Images: An Investigation of Pre-Training Datasets

X Du, Y Sun, Y Song, L Dong, X Zhao - Remote Sensing, 2023 - mdpi.com
This study introduces a novel approach to the critical task of submarine pipeline or cable
(POC) detection by employing GoogleNet for the automatic recognition of side-scan sonar …

Oil and gas automatic infrastructure mapping: Leveraging high-resolution satellite imagery through fine-tuning of object detection models

JE Guisiano, É Moulines, T Lauvaux… - … Conference on Neural …, 2023 - Springer
The oil and gas sector is the second largest anthropogenic emitter of methane, which is
responsible for at least 25% of current global warming. To curb methane's contribution to …