Optimized YOLOV8: An efficient underwater litter detection using deep learning DOI Creative Commons

Faiza Rehman,

Mariam Rehman,

Maria Anjum

et al.

Ain Shams Engineering Journal, Journal Year: 2024, Volume and Issue: 16(1), P. 103227 - 103227

Published: Dec. 26, 2024

Language: Английский

Non-Uniform Illumination Underwater Image Restoration via Illumination Channel Sparsity Prior DOI
Guojia Hou, Nan Li, Peixian Zhuang

et al.

IEEE Transactions on Circuits and Systems for Video Technology, Journal Year: 2023, Volume and Issue: 34(2), P. 799 - 814

Published: June 28, 2023

Underwater image quality is seriously degraded due to the insufficient light in water. Although artificial illumination can assist imaging, it often brings non-uniform phenomenon. To this end, we develop an channel sparsity prior (ICSP) guided variational framework for underwater restoration. Technically, built on observation that of a uniform-light HSI color space contains few pixels whose intensity very low. Then according Retinex theory, design model with L0 norm term, constraint and gradient by integrating proposed ICSP into extended formation model. Such three regularizations are effective enhancing brightness, correcting distortion, revealing structures fine-scale details. Meanwhile, exploit fast numerical algorithm base alternating direction method multipliers (ADMM) accelerate solving optimization problem. We also collect benchmark dataset, namely NUID 925 real images different illumination. Extensive experiments demonstrate our terms qualitative quantitative comparisons, ablation studies, convergence analysis, applications. The code dataset available at https://github.com/Hou-Guojia/ICSP .

Language: Английский

Citations

73
Review of intelligent detection and health assessment of underwater structures DOI
Shuai Teng, Airong Liu,

Xijun Ye

et al.

Engineering Structures, Journal Year: 2024, Volume and Issue: 308, P. 117958 - 117958

Published: April 6, 2024

Language: Английский

Citations

19
Artificial intelligence-empowered collection and characterization of microplastics: A review DOI
Pengwei Guo,

Yuhuan Wang,

Parastoo Moghaddamfard

et al.

Journal of Hazardous Materials, Journal Year: 2024, Volume and Issue: 471, P. 134405 - 134405

Published: April 26, 2024

Language: Английский

Citations

12
Surveying the deep: A review of computer vision in the benthos DOI Creative Commons
Cameron Trotter, Huw J. Griffiths, Rowan J. Whittle

et al.

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 102989 - 102989

Published: Jan. 1, 2025

Language: Английский

Citations

1
The Diversity of Artificial Intelligence Applications in Marine Pollution: A Systematic Literature Review DOI Creative Commons
Ning Jia, Shufen Pang, Zainal Arifin

et al.

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(7), P. 1181 - 1181

Published: July 14, 2024

Marine pollution, a major disturbance to the sustainable use of oceans, is becoming more prevalent around world. Multidimensional and ocean governance have become increasingly focused on managing, reducing, eliminating marine pollution. Artificial intelligence has been used in recent years monitor control This systematic literature review, encompassing studies from Web Science Scopus databases, delineates extensive role artificial pollution management, revealing significant surge research application. review aims provide information better understanding application In 57% AI applications are for monitoring, 24% 19% prediction. Three areas emphasized: (1) detecting responding oil (2) monitoring water quality its practical application, (3) identifying plastic Each area benefits unique capabilities intelligence. If scientific community continues explore refine these technologies, convergence may yield sophisticated solutions environmental conservation. Although offers powerful tools treatment it does some limitations. Future recommendations include transferring experimental outcomes industrial broader sense; highlighting cost-effective advantages control; promoting legislation policy-making about controlling

Language: Английский

Citations

4
PQGAL-Net: Perceptual Quality Guided Generative Adversarial Learning for Non-uniform Illumination Underwater Image Enhancement DOI
Jiaqi Ma, Mingzhe Wang, Guojia Hou

et al.

Digital Signal Processing, Journal Year: 2025, Volume and Issue: unknown, P. 105048 - 105048

Published: Feb. 1, 2025

Language: Английский

Citations

0
Attention-Guided Marine Debris Detection with an Enhanced Transformer Framework Using Drone Imagery DOI
L. Minh Dang, A. S. M. Sharifuzzaman Sagar, Ngoc Dung Bui

et al.

Process Safety and Environmental Protection, Journal Year: 2025, Volume and Issue: unknown, P. 107089 - 107089

Published: March 1, 2025

Language: Английский

Citations

0
Medium-Range Trajectory Prediction Network Compliant to Physical Constraint for Oceanic Eddy DOI
Linyao Ge, Baoxiang Huang, X. Chen

et al.

IEEE Transactions on Geoscience and Remote Sensing, Journal Year: 2023, Volume and Issue: 61, P. 1 - 14

Published: Jan. 1, 2023

Predicting the trajectory of ocean eddies can promote understanding transport matter and energy in ocean. However, accurately rapidly predicting poses a significant challenge due to their intricate nonlinear motion within physical environment. Regrettably, existing data-driven methods primarily focus on migration combination models, as well fusion processing diverse observational data oceanic eddies. These ways often overlook crucial aspect modeling underlying mechanism We believe that expeditious precise prediction is closely intertwined with historical time series. Consequently, medium-range eddy neural network (ETPNet) compliant constraint proposed, which embeds regulation, intrinsic relations, mutual interactions into via constraints. Then, novel variant long short-term memory (LSTM) cell designed enhance dynamic interaction representation ability features, constraints, knowledge. Finally, geographically informed comprehensive loss function for marine tasks formulated, namely mean absolute geodetic error (MAGE), optimizes Euclidean sphere space. The proposed evaluated by future seven days anticyclone $15^{\circ }\text{N}$ notation="LaTeX">$40^{\circ . extensive experiments evaluations demonstrate guided implement state-of-the-art performance. code available at https://github.com/AI4Ocean/ETPNet

Language: Английский

Citations

9
WildFishNet: Open Set Wild Fish Recognition Deep Neural Network With Fusion Activation Pattern DOI Creative Commons
Xiao-Ya Zhang, Baoxiang Huang, Ge Chen

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2023, Volume and Issue: 16, P. 7303 - 7314

Published: Jan. 1, 2023

Wild fish recognition is a fundamental problem of ocean ecology research and contributes to the understanding biodiversity. Given huge number wild species unrecognized category, essence open set fine-grained recognition. Moreover, unrestricted marine environment makes even more challenging. Deep learning has been demonstrated as powerful paradigm in image classification tasks. In this paper, deep neural network (termed WildFishNet) proposed. Specifically, an with fused activation pattern constructed implement First, three different reciprocal inverted residual structural modules are combined by structure search (NAS) obtain best feature extraction performance for recognition; Next, new fusion softmax openmax functions designed improve ability set. Then, experiments implemented on WildFish dataset that consists 54,459 unconstrained images, which includes 685 known classes 1 category. Finally, experimental results analyzed comprehensively demonstrate effectiveness proposed method. The in-depth study also shows artificial intelligence can empower ecosystem research.

Language: Английский

Citations

7
Automated marine litter investigation for underwater images using a zero-shot pipeline DOI
Tri-Hai Nguyen, Minh Hoang Dang

Environmental Modelling & Software, Journal Year: 2024, Volume and Issue: 177, P. 106065 - 106065

Published: May 7, 2024

Language: Английский

Citations

2