Search Results (476)

The detection of microleaks in subsea gas pipelines remains challenging in shallow-water environments because weak bubble-plume echoes are often obscured by seabed reverberation, ambient noise, and platform-induced interference. This study develops a custom multibeam forward-looking sonar system and a dual-domain framework for acoustic detection and localization of underwater gas microleakage. Local statistical enhancement suppresses stable background interference and strengthens anomalous bubble echoes. Blind deconvolution, adaptive grid-based thresholding, and spatial clustering then improve target sharpness, extract candidate bubble-plume regions, and reduce localized false detections. This unsupervised framework requires no pre-collected training data. It was evaluated in 30 independent sea-trial groups conducted in Bohai Bay using air to simulate leakage. Six orifice diameters from 0.5 to 3.0 mm were tested under different compressor-indicated pressures. The plume-observation distances (defined as the sonar-to-leak-device distance at the first confirmed plume response in the sonar image) ranged from 32 to 66 m across the tested conditions. Under the minimum tested condition of a 0.5 mm orifice and a compressor-indicated pressure of 0.5 MPa, the plume was observed at a distance of 32 m. The results demonstrate the feasibility of the proposed system for ROV-assisted detection and localization of subsea gas microleakage in low-visibility shallow-water environments. Full article

When LiDAR detects underwater targets, the water severely attenuates the laser beams, making it impossible to extract valid echo information during 3D reconstruction of urban water bodies. This study proposes a Multi-Scale Spectral Adaptive Loss Generative Adversarial Network Based on Morphology-Spatiotemporal Decoupled Attention (MSAGAN) that effectively enhances far-field underwater echo signals for LiDAR. Its core components consist of three parts: Morphology-Aware Dynamic Receptive Field Attention (MADRA), Spatial-Temporal Decoupled Frequency-Enhanced Global Feature Fusion Block (STDFBlock), and Adaptive Dynamic Adjustment Loss Function Based on Frequency-Domain Decomposition and Gradient Response (FGADLoss). The model precisely identifies the narrow and curved local structures of the echo signals during the feature extraction process, improving the precise detection of subtle structural changes in the echo signals and enabling the extraction of valid echo signal features from a background of numerous invalid echo signals. The model reduces image fragmentation and center-of-mass drift during echo signal augmentation, improving the accuracy of water body environments’ 3D reconstruction. Through this model, the average point cloud density per square meter for lakes and ponds increased by 2.12 and 3.54, respectively, enabling effective reconstruction of urban water bodies information and offering a high-quality data basis for underwater object recognition and bathymetric surveying. Furthermore, this method effectively addresses the challenge of simultaneously obtaining degraded and ideal streak images that match the echo signals of underwater detection targets, and it also offers advantages in terms of training data requirements, making it particularly well-suited for real-world underwater detection scenarios where paired ideal-degraded data is scarce. Full article

Underwater images are frequently degraded by wavelength-dependent absorption and scattering, resulting in color casts, low contrast, blurred textures, and loss of structural details. Existing enhancement networks may struggle to balance global context modeling, local detail recovery, and computational efficiency. To address this problem, we propose MambaUNet, an efficient U-shaped state-space network for underwater image enhancement. Its core VMEC pipeline integrates visual state-space scanning to capture long-range spatial dependencies, multi-scale alignment and adaptive aggregation to improve skip-feature coherence, efficient channel attention to recalibrate feature responses, and cross-channel state-space modeling to represent channel-dependent degradation. These components are assigned stage-specific roles within the U-shaped network, forming a spatial–scale–response–channel restoration pipeline. By coordinating these components within an encoder–decoder architecture, MambaUNet improves global tone consistency and structural recovery without relying on computationally expensive self-attention. Experiments on the full-reference LSUI and UIEB benchmarks and the no-reference C60 and S16 test sets show that the proposed network achieves competitive or superior restoration quality compared with representative conventional, CNN- or GAN-based, Transformer-based, and recent Mamba-based methods. Ablation and complexity analyses further demonstrate the complementary roles of the VMEC components and the favorable balance between enhancement quality, model size, and inference speed. MambaUNet can therefore serve as a lightweight preprocessing component for underwater imaging and vision-based applications. Full article

Underwater laser imaging is widely used for deep-sea exploration, autonomous underwater navigation, and inspection of marine infrastructure, where high-precision observation under optically challenging conditions is required. These imaging systems are inherently limited by absorption attenuation, volume scattering, and backscattered noise, leading to reduced visibility, low contrast, and loss of structural details. In this study, we propose a Polarization-Constrained Multi-Scale Defogging and Restoration (PCMS-DR) algorithm designed for turbid and heterogeneous aquatic environments, specifically targeting submerged engineered structures, pipelines, and other objects of interest. The method integrates polarization feature constraints with multi-scale decomposition, enabling robust separation of backscattered light and target-reflected signals while preserving high-frequency structural information. To quantitatively evaluate the proposed framework, two complementary validation strategies are adopted. First, polarization-resolved Monte Carlo photon propagation simulations are conducted to generate physically consistent synthetic underwater laser images for controlled analysis under different scattering conditions. Second, real-world validation is performed using 12 self-acquired coastal underwater laser imaging scenes collected under representative aquatic environments. The simulation and experimental datasets are analyzed separately to ensure that the quantitative evaluation accurately reflects both physical restoration capability and practical applicability. Quantitative results from the Monte Carlo simulation experiments demonstrate that the proposed PCMS-DR method achieves a peak PSNR of 26.52 dB and an SSIM of 0.836 under representative low-turbidity conditions, outperforming polarization-only and multi-scale-only baselines. In addition, evaluation on the self-acquired real underwater laser imaging dataset containing 12 coastal scenes indicates an average backscatter suppression ratio of 22.3% and a local contrast enhancement ratio of 1.62. These results confirm that the proposed method improves image visibility and structural preservation across both controlled simulations and practical imaging scenarios. Furthermore, evaluation on 12 real coastal underwater laser imaging scenes demonstrates an average backscatter suppression ratio of 22.3% and a local contrast enhancement ratio of 1.62, indicating improved visibility, contrast, and structural fidelity. The principal novelty of the proposed framework lies in the unified integration of polarization-constrained backscatter modeling, multi-scale transmission estimation, and physically guided detail restoration within a single optimization framework. The experimental results demonstrate that the proposed PCMS-DR framework provides physically interpretable and effective restoration performance under the tested turbidity range for underwater laser imaging applications. Full article

This paper presents a novel approach for estimating 3D human pose from monocular video sequences in underwater scenarios, tackling the unique challenges posed by water refraction, body occlusion, low image quality and illumination distortion in underwater environments. Leveraging both 2D keypoint extraction and parametric model estimation, our method operates in a two-stage framework including preprocessing and optimization. In the preprocessing stage, a Part Attention Regressor (PARE) is adopted to dynamically estimate SMPL human body parameters, particularly adept at handling occlusions common in underwater scenarios. Additionally, a 2D keypoint detector, employing YOLO for bounding box detection and HRNet for keypoint regression, enhances feature extraction despite underwater image challenges. In the optimization stage, we propose an underwater variational autoencoder (UW-VAE), which adopts a data-driven strategy to learn the biomechanical prior distribution of underwater human poses and implicitly correct unreasonable pose parameters caused by refraction and occlusion. The optimization process incorporates constraints aligning final SMPL models with detected 2D keypoints, minimizing disparity between adjusted and original SMPL models, and ensuring temporal consistency. Furthermore, to address the scarcity of annotated underwater datasets, we build a full pipeline to generate synthetic underwater datasets with complete annotations based on UW-VAE. Experimental results on the SwimXYZ synthetic dataset show that our method achieves 51.60% PCK@0.2 and 80.13% PCK@0.5, outperforming state-of-the-art land-based methods across most stroke categories. Validation on real-world underwater swimming datasets demonstrates improved 2D keypoint accuracy after synthetic-data fine-tuning, which provides a new solution for 3D human motion analysis in underwater sports, biomechanical research and swimming training. Full article

Underwater images often suffer from color distortion, low contrast, and structural blurring caused by wavelength-dependent absorption and scattering, which degrade both visual observation and downstream perception. Existing underwater image enhancement methods usually learn image-level restoration mappings, while the relationships among semantic regions, degradation patterns, and restoration responses are not fully exploited. In this paper, we propose a Semantic Guidance Network with Degradation Consistency for Underwater Image Enhancement (SGDC-UIE). Specifically, SGDC-UIE first extracts dense semantic responses from a frozen DINOv3 prior and converts them into foreground, boundary, and background region gates. These gates are then used to guide pseudo-physical degradation estimation, producing attenuation-like, transmission-like, illumination, structure, and background-light priors for region-aware restoration. These pseudo-physical priors are learned, bounded conditioning variables rather than calibrated estimates of underwater optical parameters. Based on these degradation conditions, a dual-branch restoration network corrects low-frequency color and illumination degradation while recovering high-frequency structural details through semantic-aware wavelet restoration. The color-restored and structure-restored outputs are further integrated by a degradation-consistent fusion gate, which adaptively balances visual fidelity and task-relevant structure preservation. In addition, grouped supervision with quality-anchor replay stabilizes task-aware fine-tuning and reduces visual-quality drift. Extensive experiments on paired and no-reference underwater enhancement benchmarks, semantic segmentation, and underwater object detection show that SGDC-UIE achieves competitive restoration quality and improves the usability of enhanced images for downstream perception. Full article

Underwater object detection is a fundamental task in underwater sensing and is generally approached using either optical or sonar sensors. Although optical imaging provides rich semantic information, it is highly susceptible to water turbidity and illumination variations. By contrast, sonar imaging can effectively overcome visibility limitations, yet it suffers from severe speckle noise and blurred object contours. Moreover, resource-limited platforms impose strict demands on model lightweightness and real-time performance. To this end, this paper proposes a novel cross-modal heterogeneous distillation method (CMHD) to balance detection accuracy and computational complexity. CMHD performs cross-modal knowledge transfer by leveraging the rich semantics of RGB images to enhance sonar feature representation, compensating for the information deficiency of the sonar modality. Meanwhile, a heterogeneous distillation scheme compresses the detection capability of a high-capacity teacher YOLOX-M into a lightweight student YOLOX-S-Ghost, enabling strong feature extraction under a highly compact model. To mitigate the modality gap and geometric inconsistency between RGB and sonar modalities, we design a branch-aware heterogeneous distillation strategy. To improve detection accuracy and reduce model parameters, the student network incorporates Coordinate Attention (CA) in its backbone and adopts a lightweight neck design. Experiments on the UXO^† dataset demonstrate that CMHD achieves 79.6% mAP and 82.6% mAR, significantly outperforming the compared representative methods and serving as an accurate, efficient, and lightweight solution for underwater sonar object detection. Full article

Underwater laser range-gated imaging (ULRGI) effectively suppresses water backscattering via time-slicing mechanisms, making it a primary modality for underwater vision. However, factors such as the inherent optical properties of water, intra-slice residual scattering, gating timing errors, and sensor noise make it difficult to separate target signals from the background. Consequently, the resulting images are generally affected by texture degradation and low contrast, severely limiting the accuracy of downstream tasks like object detection and environmental perception. To this end, we propose the use of a Wavelet-guided Multi-stage Gated Enhancement Network (WMGNet). Operating progressively across three stages, WMGNet’s first two stages employ an encoder–decoder architecture that leverages multi-scale frequency decomposition in the wavelet domain to pinpoint intra-slice scattering and decouple target signals from noise. To precisely extract fine details, we design a TextureBlock integrating feature gating (ConvGLU) and high-frequency attention (HFAttention). Additionally, a pixel-wise ground-truth guided attention module (GGAM) is introduced to optimize the precision and target-specificity of multi-stage feature fusion. Extensive comparative and ablation experiments demonstrate that the proposed WMGNet effectively eliminates scattering interference and restores texture details in underwater imaging. On our custom ULRGI dataset, it achieves state-of-the-art performance with a PSNR of 36.31 dB, an SSIM of 0.921, an MAE of 2.672, and an LPIPS of 0.060. Notably, it outperforms the second-best method by a margin of 3.06 dB in PSNR and reduces the MAE by 50.69%. Furthermore, evaluations on three public datasets confirm its robust cross-scenario generalization, yielding competitive PSNR values of 33.22 dB, 31.59 dB, and 32.06 dB, respectively. Overall, WMGNet provides a highly effective and robust solution for high-resolution underwater imaging. Full article

Underwater object detection plays a vital role in marine exploration and resource exploitation. However, complex underwater environment leads to severe color deviation, blurring, and information loss of small targets, which greatly restrict detection performance. To address these problems, this paper integrates the Channel Attention and Spatial Attention Block (CASAB) attention mechanism into residual blocks based on generative adversarial networks to correct color distortion and improve the clarity of degraded underwater images. For underwater small object detection, MobileNetV2 is selected as the backbone network within the Faster R-CNN framework, and a multi-scale feature fusion strategy is adopted to reduce feature loss caused by repeated downsampling. In the detection head, coordinate attention and parallel dilated convolution are further integrated to suppress background noise and expand the receptive field of feature extraction. Experimental results on the Underwater Robot Professional Contest (URPC) dataset demonstrate that the proposed method yields gains of 10.06%, 9.43%, and 12.29% in three evaluation metrics: Underwater Image Quality Measure (UIQM), Underwater Colour Image Quality Evaluation (UCIQE) and Natural Image Quality Evaluator (NIQE), together with 7.81% in Mean Average Precision (mAP) and an 8.57% increase in Mean Recall (mRecall). These results demonstrate the effectiveness of all improvements. Full article

Underwater images exhibit severe colour distortion, low contrast, and blurred details due to light absorption and scattering, which limits their practical use in marine applications. Existing methods face poor generalisation, high computational costs and weak integration of physical priors. To address these issues, this paper proposes TIDE-Net, a triple-branch illumination and detail enhancement network for underwater images. It decomposed inputs into illumination, reflectance intensity, and chromaticity branches for parallel optimisation, enabling decoupled handling of brightness, texture, and colour degradation. A piecewise colour correction module mitigated complex colour casts without introducing artefacts; a lightweight U-Net branch enhanced fine details while suppressing noise; and a local gain compensation module improved brightness uniformity and reduced halo effects. Experiments on four datasets showed that TIDE-Net outperforms some state-of-the-art methods, achieving a PSNR of 29.44 dB, an SSIM of 0.94, and competitive UIQM/UCIQE scores with only 7.74 M parameters. The results confirmed that the proposed triple-branch strategy effectively balances physical interpretability, restoration quality, and computational efficiency. In conclusion, TIDE-Net provides a robust and lightweight solution suitable for deployment on resource-limited underwater platforms, offering practical value for real-world underwater vision tasks. Full article

Underwater detection is crucial for the autonomous operation of Autonomous Underwater Vehicles (AUVs). However, underwater environments pose significant challenges, including severe image degradation, complex target deformation, and densely distributed small objects. Most existing methods treat image enhancement as an independent preprocessing module and rely on fixed-shape convolution kernels for feature extraction, which often leads to inconsistent optimization objectives and limited capability in handling irregular targets and fine-grained small-object details. To address these issues, we propose an End-to-End Adaptive Underwater Detection framework (E2E-AUD). Specifically, a lightweight image enhancement module, UnitModule, is embedded into the detection network so that enhancement can be jointly optimized with detection and directly serve downstream feature learning. In addition, linear deformable convolution (LDConv) is introduced into the backbone to adaptively model polymorphic targets, while Haar wavelet downsampling (HWD) is adopted to preserve boundary and texture information through frequency-domain analysis. Experiments on the DUO and URPC datasets demonstrate that E2E-AUD achieves superior performance over both general-purpose and underwater-specific detectors. Specifically, on the DUO dataset, our model reaches 86.2% mAP50 and 67.8% mAP50-95, outperforming the recent YOLOv12 by 3.0% and 2.7%, respectively. On the highly turbid URPC dataset, it achieves 84.3% mAP50 and 50.8% mAP50-95, surpassing the competitive underwater-specific detector LEFEN by notable margins in strict localization metrics. Furthermore, E2E-AUD maintains a real-time inference speed of 21.8 FPS with highly constrained computational complexity (9.4 GFLOPs), proving its exceptional balance between detection accuracy and deployment efficiency compared to previous methods. Full article

Underwater images often suffer from color cast, low contrast, scattering-induced haze, and texture degradation, which limit the performance of underwater visual perception systems. To address these problems, this study proposes FreqMambaGAN, a frequency-decoupled selective state-space cycle-adversarial network for underwater image enhancement. The proposed method is built upon a CycleGAN-style bidirectional translation framework and introduces a frequency-decoupled Mamba generator to separately model low-frequency color and illumination information and high-frequency texture and edge details. In addition, Efficient Mamba Blocks are embedded into the generator and discriminator to enhance long-range dependency modeling with linear computational complexity. Skip-attention connections are further adopted to preserve shallow spatial details during reconstruction. To improve training stability and imaging plausibility, a multi-stage training strategy is designed by combining supervised warm-up, unpaired cycle-adversarial learning, perceptual regularization, total variation smoothing, and a lightweight physics-inspired consistency constraint based on dark-channel and underwater image-formation priors. Experiments on public underwater image enhancement datasets demonstrate that FreqMambaGAN achieves competitive quantitative performance and visually improved enhancement results in terms of color correction, contrast restoration, haze suppression, and structural preservation. These results indicate that integrating frequency-domain decomposition with selective state-space modeling is effective for underwater image enhancement. Full article

This paper presents a systematic evaluation framework for underwater image enhancement (UIE), focusing on reliable quality assessment for vision applications in challenging underwater environments. The framework jointly analyzes subjective visual quality and objective image quality assessment measures. A controlled, laboratory-based subjective study following the ITU-R absolute category rating protocol is conducted on two datasets: UIEBD (with and without quasi-reference images) and the EUVP validation subset. A total of 132 images from UIEBD and 120 images from EUVP are evaluated, including enhanced images from four recent deep learning-based UIE models (CCL-Net, HUPE, GuidedHybSensUIR, and UDNet). The subjective results reveal dataset-dependent behavior of the evaluated methods, highlighting the challenges of reliable perceptual evaluation in the presence of diverse degradations and quasi-reference data. Objective analysis shows that modern learning-based, no-reference image quality assessment (NR-IQA) models exhibit higher correlation with subjective mean opinion scores than traditional underwater-specific measures. In particular, TOPIQ_NR achieves a Spearman correlation of 0.80 on UIEBD and remains among the top-performing methods on EUVP, where LIQE reaches 0.87, while widely used measures such as UIQM and UCIQE show weaker alignment with human perception. These findings support the adoption of learning-based NR-IQA measures for robust underwater vision systems. Full article

The unique nature of polarization information can provide a reliable physical prior for underwater multimodal image fusion. Existing methods mainly employ the integration of linearly polarized images from multiple directions, which is essentially an intensity fusion process of images. To solve this problem, we propose an underwater polarization imaging technology based on multi-polarization modality fusion. This method employs the total intensity S₀ to provide the basic scene brightness, uses the degree of linear polarization (DoLP) as a physical prior, fully exploits the rich texture features in DoLP to compensate for S₀, and integrates color information channels to better preserve the color characteristics of the scene. In addition, we develop a Polarization Feature Enhancement Module (PFEM) tailored for polarization data, which embeds a customized gating mechanism to select features and adaptively fuse feature vectors from different channels. Finally, we construct and publicly release an underwater polarization image dataset with multiple turbidity levels and materials, and systematically verify the robustness of the proposed method. Full article

Side-scan sonar (SSS) imaging plays a critical role in underwater perception for autonomous underwater vehicles (AUVs). However, the spatial sparsity of targets and the limited computational resources remain challenging for real-time object detection. Existing methods typically adopt dense inference strategies, leading to substantial computational redundancy and limited deployment feasibility. In this work, we propose a lightweight and ultra-fast SSS object detection framework based on target presence awareness. The proposed framework follows a coarse-to-fine inference paradigm, in which a target presence analysis module is first employed to rapidly filter out target-absent image patches, and only target-positive patches are forwarded to an Object Forward Detection (OFD) module for fine-grained detection. The TPA module integrates spatial–frequency convolution to efficiently capture both local structural cues and global contextual information with minimal computational overhead. Furthermore, an AttnConv-enhanced detection module is introduced in the OFD stage to strengthen high-frequency target features and improve fine-grained detection performance. Extensive experiments on public SSS datasets demonstrate that the proposed method achieves an mAP of 74.63% on the AI4Shipwrecks dataset and 63.02% on the SSS-Mine dataset. Notably, the framework delivers an ultra-fast inference speed of 174.74 FPS on embedded hardware, representing a 5.2× speedup over conventional dense-processing detection methods. Full article