Underwater Images Research Articles (Page 1)

Precise underwater classification of small aquaculture species is essential for sustainable fisheries management, biodiversity monitoring, and automated marine ecosystem analysis. But it is still a challenging task owing to underwater image distortions from poor visibility, lighting changes, occlusions, and the high computational complexity of traditional deep learning models. To address these issues, we propose a Lightweight Variational Quantum Enhanced Deep Transfer Learning framework. This hybrid deep transfer learning model integrates pretrained classical convolutional neural networks with variational quantum circuits to improve feature representation and classification efficiency. The framework is designed to reduce computational complexity while enhancing accuracy by leveraging quantum feature extraction techniques. Experimental evaluations on curated small aquafarming species dataset demonstrate that the proposed approach achieves high classification accuracy (up to 99.25%) with significantly fewer parameters and floating-point operations, indicating its potential for resource-constrained applications. Ablation studies further validate the impact of quantum layers on model performance. These results suggest that quantum deep transfer learning models can offer a promising direction for robust and efficient underwater species classification.

CDMM: conditional diffusion model with mamba for low-light underwater image enhancement

In hazy weather, the quality of aerial images suffers severe degradation, which affects the imaging capabilities of advanced remote sensing applications. Most existing learning-based dehazing algorithms utilize manually designed deep structures to enhance model performance. However, these deep networks often contain redundant branches, leading to a significant decrease in computational efficiency. To address this issue, we first conduct experiments to explore the distribution of haze and introduce an improved dehazing strategy in the YUV space. Subsequently, we propose a Runge-Kutta (RK) method-inspired aerial image dehazing network called RKNet, which consists of two parts: luminance (Y) domain haze removal and chrominance (U,V) enhancement. From the perspective of dynamical systems and based on the 3rd-order RK method, we design an RK3 block and incorporate it into RKNet to improve computational accuracy. Experimental evaluations on both synthetic and real-world benchmarks demonstrate that RKNet outperforms current haze removal algorithms and achieves superior performance. In addition, RKNet can improve the detection accuracy and capability of high-level vision algorithms and is also applicable to the processing of sandstorm images and underwater images.

Abstract Underwater infrastructures such as pipelines, ship hulls, and offshore platforms are critical to marine operations but are highly vulnerable to biofouling, structural corrosion, and vegetation overgrowth, leading to increased maintenance costs and environmental hazards. However, visual inspection of these structures remains challenging due to low visibility, uneven lighting, and complex textured surfaces that limit the effectiveness of both traditional and purely deep learning-based approaches. In this work, we introduce AquaFusionNet, a hybrid defect classification framework that seamlessly integrates embeddings from four state-of-the-art pre-trained backbones (EfficientNet-B0, ResNet-50, SENet-50, and Vision Transformer) with complementary traditional descriptors including colour histograms, histogram of oriented gradients (HOG), local binary patterns (LBP), edge density, and gradient statistics via a trainable attention module. This attention mechanism dynamically weights each feature channel, allowing the model to emphasise the most informative cues while preserving fine-scale details under variable turbidity and illumination. We evaluate AquaFusionNet on a curated dataset of 2,228 underwater images spanning three defect categories, with 445 images held out for testing. Our model achieves 98.43% accuracy, 98.18% precision, 97.79% recall, a 96.06% intersection-over-union, and a 97.97% F $$_1$$ -score, outperforming eleven strong baselines, including ResNet-152 and EfficientNet-B0, by a substantial margin. These results demonstrate AquaFusionNet’s robustness and generalisability, paving the way for real-time, automated underwater inspection systems that can significantly enhance operational safety and reduce maintenance costs across marine industries. Graphic Abstract This graphical abstract provides a clear overview of the AquaFusionNet research, illustrating a streamlined workflow moving from data acquisition through final results and conclusions. The dataset comprises 2,228 underwater images categorized into biofouling, holes, and vegetation, sourced from the ICIP MVI-2024 challenge and split into training, validation, and testing subsets with a ratio of 60:20:20. The analysis phase emphasizes preprocessing steps combined with traditional descriptors, including color histograms, texture patterns, and gradient-based features, complementing the extracted deep features. The AquaFusionNet model uniquely integrates embeddings from four advanced, lightweight backbones, EfficientNet-B0, ResNet-50, SE-ResNet-50, and Vision Transformer (ViT-B/16) with traditional features, using a dynamic trainable attention mechanism. This attention module adaptively emphasizes the most informative features, which are then classified via a two-layer multilayer perceptron (MLP). Evaluation of the model reveals exceptional performance metrics, achieving an accuracy of 98.43%, an F1-score of 97.97%, and an intersection-over-union (IoU) of 96.06%, surpassing eleven state-of-the-art models on a test set of 445 images. The final conclusion highlights AquaFusionNet as an efficient, deployment-ready framework capable of robustly detecting underwater defects, significantly enhancing the safety and reducing the costs associated with marine inspections.

Real-time underwater image enhancement via multi-path collaborative network with low-resolution guidance

Feasibility of underwater true color three-dimensional imaging using hyperspectral LiDAR

Multi-scale integration with semantic embedding and adaptive excitation transformer for underwater optical image enhancement

UNCORE: an underwater lightweight image enhancement via neutrosophic color restoration and refinement

Policy, management, and the 'Level of Fouling' scale to transform marine invasion risk reduction from recreational boats.

Zero-dimensional hydrostable copper(I) halides for underwater X-ray imaging

Polarization-constrained Global-local gated adaptive fusion network for underwater polarization imaging

Underwater polarization image enhancement based on low-rank polarization tensor model

An efficient underwater image enhancement framework using optimized color correction and texture restoration

LALG: Underwater image enhancement via luminance-aware variational color correction and joint local-global contrast restoration

Underwater image captioning via attention mechanism based fusion of visual and textual information

Method for Enhancing Underwater Images based on Optimized Multi-Scale Structures

Underwater image enhancement based on visual perception fusion

Abstract Computational ghost imaging faces significant performance degradation in dynamic oceanic turbulence. This study proposes a ‘orthogonal basis + controllable randomization’ principle to design robust speckle patterns. We establish a multi-level evaluation system to analyze six types of speckles, revealing a dual mechanism: orthogonality suppresses mode degradation while randomization enhances turbulence adaptability. Results demonstrate that the synergistic design (e.g. orthogonal random speckle) significantly outperforms classical orthogonal speckles in maintaining structural integrity and suppressing crosstalk under strong turbulence. Furthermore, different randomization strategies (global vs block-wise) offer adaptable performance trade-offs between stability and fidelity. This work addresses the lack of dynamic optimization criteria in speckle design, providing a potential solution for high-resolution underwater imaging.

Scene-aware atmospheric light estimation and superpixel transmission model for underwater image restoration

Cross-scale coupled attention network for underwater image enhancement