Search Results (247)

Accurately predicting the long-term behavior of complex dynamical systems is a central challenge for safety-critical applications like autonomous navigation. Mechanistic models are often brittle, relying on difficult-to-measure parameters, while standard deep learning models are black boxes that fail to generalize, producing physically inconsistent predictions. Here, we introduce a physics-informed framework that learns the continuous-time dynamics of an Autonomous Underwater Vehicle (AUV) by discovering its underlying energy landscape. We embed the structure of Port-Hamiltonian mechanics into a neural ordinary differential equation (NODE) architecture, learning not to imitate trajectories but rather to identify the system’s Hamiltonian and its constituent physical matrices from observational data. Geometric consistency is enforced by representing rotational dynamics on the SE(3) manifold, preventing numerical error accumulation. Experimental validation reveals a stark performance divide. While a state-of-the-art black-box model matches our accuracy in simple, interpolative maneuvers, its predictions fail catastrophically under complex controls. Quantitatively, our physics-informed model maintained a mean 10 s position error of a mere 3.3 cm, whereas the black-box model’s error diverged to 5.4 m—an over 160-fold performance gap. This work establishes that the key to robust, generalizable models lies not in bigger data or deeper networks but in the principled integration of physical laws, providing a clear path to overcoming the brittleness of black-box models in critical engineering simulations. Full article

Autonomous navigation in GPS-denied, unstructured environments such as murky waters or complex seabeds remains a formidable challenge for robotic systems, primarily due to sensory degradation and the computational inefficiency of conventional algorithms. Drawing inspiration from the robust navigation strategies of marine species such as the sea turtle’s quantum-assisted magnetoreception, the octopus’s tactile-chemotactic integration, and the jellyfish’s energy-efficient flow sensing this study introduces a novel neuromorphic framework for resilient robotic navigation, fundamentally based on the co-design of marine-inspired sensors and event-based neuromorphic processors. Current systems lack the dynamic, context-aware multisensory fusion observed in these animals, leading to heightened susceptibility to sensor failures and environmental perturbations, as well as high power consumption. This work directly bridges this gap. Our primary contribution is a hybrid sensor fusion model that co-designs advanced sensing replicating the distributed neural processing of cephalopods and the quantum coherence mechanisms of migratory marine fauna with a neuromorphic processing backbone. Enabling real-time, energy-efficient path integration and cognitive mapping without reliance on traditional methods. This proposed framework has the potential to significantly enhance navigational robustness by overcoming the limitations of state-of-the-art solutions. The findings suggest the potential of marine bio-inspired design for advancing autonomous systems in critical applications such as deep-sea exploration, environmental monitoring, and underwater infrastructure inspection. Full article

The quality of underwater imagery is inherently degraded by light absorption and scattering, a challenge that severely limits its application in critical domains such as marine robotics and archeology. While existing enhancement methods, including recent hybrid models, attempt to address this, they often struggle to restore fine-grained details without introducing visual artifacts. To overcome this limitation, this work introduces a novel hybrid U-Net-Transformer (UTR) architecture that synergizes local feature extraction with global context modeling. The core innovation is a Recurrent Multi-Scale Feature Modulation (R-MSFM) mechanism, which, unlike prior recurrent refinement techniques, employs a gated modulation strategy across multiple feature scales within the decoder to iteratively refine textural and structural details with high fidelity. This approach effectively preserves spatial information during upsampling. Extensive experiments demonstrate the superiority of the proposed method. On the EUVP dataset, UTR achieves a PSNR of 28.347 dB, a significant gain of +3.947 dB over the state-of-the-art UWFormer. Moreover, it attains a top-ranking UIQM score of 3.059 on the UIEB dataset, underscoring its robustness. The results confirm that UTR provides a computationally efficient and highly effective solution for underwater image enhancement. Full article

Detecting underwater structural defects is vital for hydraulic engineering safety. Diverse patterns of underwater structural defects, i.e., the morphology and scale characteristics, pose difficulties on feature representability during detection. Any single feature morphology is insufficient to fully characterize diverse types of underwater defect patterns. This paper proposes a novel hybrid neural network to enhance feature representation of underwater structural multi-defects, which in turn improves the accuracy and adaptability of underwater detection. Three types of convolution operations are combined to build Hybrid Aggregation Network (HanNet), enhancing the morphological representation for diverse defects. Considering the scale difference of diverse defects, the Multi-Scale Shared Feature Pyramid (MSFP) is proposed, facilitating adaptive representation for diverse sizes of structural defects. The defect detection module leverages an Adaptive Spatial-Aware Attention (ASAA) at the backend, enabling selective enhancement of salient defect features. For model training and evaluation, we, for the first time, build an underwater structural multi-defects sonar image dataset containing a wide range of typical defect types. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods, significantly improving defect detection accuracy, and provides an effective solution for detecting diverse structural defects in complex underwater environments. Full article

Focusing on visual target detection for Autonomous Underwater Vehicles (AUVs), this paper investigates enhancement methods for weakly illuminated underwater images, which typically suffer from blurring, color distortion, and non-uniform illumination. Although deep learning-based approaches have received considerable attention, existing methods still face limitations such as insufficient feature extraction, poor detail detection, and high computational costs. To address these issues, we propose RECAD—a lightweight and efficient underwater image enhancement method based on Retinex theory. The approach incorporates a dark region detection mechanism to significantly improve feature extraction from low-light areas, along with an efficient channel attention module to reduce computational complexity. A residual learning strategy is adopted in the image reconstruction stage to effectively preserve structural consistency, achieving an SSIM value of 0.91. Extensive experiments on the UIEB and LSUI benchmark datasets demonstrate that RECAD outperforms state-of-the-art models including FUnIEGAN and U-Transformer, achieving a high SSIM of 0.91 and competitive UIQM scores (up to 3.19), while improving PSNR by 3.77 dB and 0.69–1.09 dB, respectively, and attaining a leading inference speed of 97 FPS, all while using only 0.42 M parameters, which substantially reduces computational resource consumption. Full article

The field of underwater image enhancement (UIE) has advanced significantly, yet it continues to grapple with persistent challenges stemming from complex, spatially varying optical degradations such as light absorption, scattering, and color distortion. These factors often impede the efficient deployment of enhancement models. Conventional approaches frequently rely on uniform processing strategies that neither adapt effectively to diverse degradation patterns nor adequately incorporate physical principles, resulting in a trade-off between enhancement quality and computational efficiency. To overcome these limitations, we propose a Dual-Path Physics-Guided Mamba Network (DPPGM), a lightweight framework designed to synergize physical optics modeling with data-driven learning. Extensive experiments on three benchmark datasets (UIEB, LSUI, and U45) demonstrate that DPPGM outperforms 13 state-of-the-art methods, achieving an exceptional balance with only 1.48 M parameters and 25.39 G FLOPs. The key to this performance is a symmetry-constrained architecture: it incorporates a dual-path Mamba module for degradation-aware processing, physics-guided optimization based on the Jaffe–McGlamery model, and compact subspace fusion, ensuring that quality and efficiency are mutually reinforced rather than competing objectives. Full article

Underwater wireless communication (UWC) is an emerging technology crucial for automating marine industries, such as offshore aquaculture and energy production, and military applications. It is a key part of the 6G vision of creating a hyperconnected world for extending connectivity to the underwater environment. Of the three main practicable UWC technologies (acoustic, optical, and radiofrequency), acoustic methods are best for far-reaching links, while optical is best for high-bandwidth communication. Recently, utilizing reconfigurable intelligent surfaces (RISs) has become a hot topic in terrestrial applications, underscoring significant benefits for extending coverage, providing connectivity to blind spots, wireless power transmission, and more. However, the potential for further research works in underwater RIS is vast. Here, for the first time, we conduct an extensive survey of state-of-the-art of RIS and metasurfaces with a focus on underwater applications. Within a holistic perspective, this survey systematically evaluates acoustic, optical, and hybrid RIS, showing that environment-aware channel switching and joint communication architectures could deliver holistic gains over single-domain RIS in the distance–bandwidth trade-off, congestion mitigation, security, and energy efficiency. Additional focus is placed on the current challenges from research and realization perspectives. We discuss recent advances and suggest design considerations for coupling hybrid RIS with optical energy and piezoelectric acoustic energy harvesting, which along with distributed relaying, could realize self-sustainable underwater networks that are highly reliable, long-range, and high throughput. The most impactful future directions seem to be in applying RIS for enhancing underwater links in inhomogeneous environments and overcoming time-varying effects, realizing RIS hardware suitable for the underwater conditions, and achieving simultaneous transmission and reflection (STAR-RIS), and, particularly, in optical links—integrating the latest developments in metasurfaces. Full article

Accurate and efficient detection of underwater targets in sonar imagery is critical for applications such as marine exploration, infrastructure inspection, and autonomous navigation. However, sonar-based object detection remains challenging due to low resolution, high noise, cluttered backgrounds, and the scarcity of annotated data. To address these issues, we propose UWS-YOLO, a novel detection framework specifically designed for underwater sonar images. The model integrates three key innovations: (1) a C2F-Ortho module that enhances multi-scale feature representation through orthogonal channel attention, improving sensitivity to small and low-contrast targets; (2) a DySnConv module that employs Dynamic Snake Convolution to adaptively capture elongated and irregular structures such as pipelines and cables; and (3) a cross-modal transfer learning strategy that pre-trains on large-scale optical underwater imagery before fine-tuning on sonar data, effectively mitigating overfitting and bridging the modality gap. Extensive evaluations on real-world sonar datasets demonstrate that UWS-YOLO achieves a mAP@0.5 of 87.1%, outperforming the YOLOv8n baseline by 3.5% and seven state-of-the-art detectors in accuracy while maintaining real-time performance at 158 FPS with only 8.8 GFLOPs. The framework exhibits strong generalization across datasets, robustness to noise, and computational efficiency on embedded devices, confirming its suitability for deployment in resource-constrained underwater environments. Full article

Underwater crack detection is critical for ensuring the safety and longevity of submerged infrastructures, yet it remains challenging due to water-induced image degradation, limited labeled data, and the poor generalization of existing models. This paper proposes a novel deep learning framework that integrates physical priors and uncertainty modeling to address these challenges. Our approach introduces a physics-guided enhancement module that leverages underwater light propagation models, and a dual-branch segmentation network that combines semantic and geometry-aware curvature features to precisely delineate irregular crack boundaries. Additionally, an uncertainty-aware Transformer module quantifies prediction confidence, reducing the number of overconfident errors in ambiguous regions. Experiments on a self-collected dataset demonstrate State-of-the-Art performance, achieving 81.2% mIoU and 83.9% Dice scores, with superior robustness in turbid water and uneven lighting. The proposed method introduces a novel synergy of physical priors and uncertainty-aware learning, advancing underwater infrastructure inspection beyond the current data-driven approaches. Our framework offers significant improvements in accuracy, robustness, and interpretability, particularly in challenging conditions like turbid water and non-uniform lighting. Full article

Underwater images frequently exhibit color distortion, detail blurring, and contrast degradation due to absorption and scattering by the underwater medium. This study proposes a progressive color correction strategy integrated with a vision-inspired image enhancement framework to address these issues. Specifically, the progressive color correction process includes adaptive color quantization-based global color correction, followed by guided filter-based local color refinement, aiming to restore accurate colors while enhancing visual perception. Within the vision-inspired enhancement framework, the color-adjusted image is first decomposed into a base layer and a detail layer, corresponding to low- and high-frequency visual information, respectively. Subsequently, detail enhancement and noise suppression are applied in the detail pathway, while global brightness correction is performed in the structural pathway. Finally, results from both pathways are fused to yield the enhanced underwater image. Extensive experiments on four datasets verify that the proposed method effectively handles the aforementioned underwater enhancement challenges and significantly outperforms state-of-the-art techniques. Full article

Museums offer significant value by preserving cultural heritage, fostering education and intellectual curiosity, and promoting social interaction, contributing to economic development and environmental sustainability. Underwater museums are relatively new and innovative and the Museum of Underwater Art, (MOUA) installed in 2017 in the Great Barrier Reef, Australia, offers an inspiring and educational experience that encourages positive conversations and garners significant media attention. Through a blend of art and science, MOUA provides a unique educational opportunity and initiates reef conversations on the challenging issues of citizen science, climate change, and coral bleaching, inviting snorkelers, divers, and the general community to protect the Great Barrier Reef. The MOUA asset is valued at $4 M and generates approximately $100 K per year from grants and earned income. The MOUA sculptures are seen by approximately 1.5 M people per year with the highest interactions associated with The Ocean Siren sculpture and approximately four thousand snorkelers and SCUBA divers a year visit the remote Coral Greenhouse and Ocean Sentinels sculptures at John Brewer Reef on commercial tourism trips. The MOUA has a large media reach of over 22 million. The Museum of Underwater Art demonstrates how art and culture can amplify reef conservation, achieving global research and community engagement beyond its small scale. This case study also exposes gaps in how ocean sustainability is measured across reef organizations and highlights the methodologies to fulfill those knowledge gaps. Our paper assesses Key Performance Indicators across other institutions and proposes methods to shift and improve conservation paradigms by the inclusion of cultural storytelling, citizen science, education, and carbon neutral events. Full article

Imaging through dynamic scattering media remains a fundamental challenge because of severe information loss and the ill-posed nature of the inversion problem. Conventional methods often struggle to strike a balance between reconstruction fidelity and efficiency in evolving environments. In this study, we present DynaFlowNet, a framework that leverages conditional flow matching theory to establish a continuous, invertible mapping from speckle patterns to target images via deterministic ordinary differential equation (ODE) integration. Central to this is the novel temporal–conditional residual attention block (TCResAttnBlock), which is designed to model spatiotemporal scattering dynamics. DynaFlowNet achieves real-time performance at 134.77 frames per second (FPS), which is 117 times faster than diffusion-based models, while maintaining state-of-the-art reconstruction quality (28.46 dB peak signal-to-noise ratio (PSNR), 0.9112 structural similarity index (SSIM), and 0.8832 Pearson correlation coefficient (PCC)). In addition, the proposed framework demonstrates exceptional geometric generalization, with only a 1.05 dB PSNR degradation across unseen geometries, significantly outperforming existing methods. This study establishes a new paradigm for real-time high-fidelity imaging using dynamic scattering media, with direct implications for biomedical imaging, remote sensing, and underwater exploration. Full article

The global demand for innovative underwater applications is increasing, encompassing scientific research, commercial endeavors, and defense operations. A significant challenge these applications face is fulfilling the energy requirements of underwater devices. This challenge extends beyond powering individual devices to include the entire network of underwater robotic sensors. These devices have varying energy needs; some are mobile while others are stationary, and they operate under diverse environmental conditions, such as different depths, temperatures, pressures, currents, and salinity levels. This paper compares the latest state-of-the-art research on powering underwater devices, addressing the challenges and practical considerations. It examines two primary approaches: first, energy harvesting from the natural environment, and second, the use of wireless power transfer (WPT). While energy harvesting methods have been established, their effectiveness greatly depends on the specific environment in which they are deployed, making them less viable as a universal solution. On the other hand, WPT presents its challenges, particularly as its efficiency diminishes with distance. Nonetheless, it remains a promising option, and further research is essential to explore its potential, including the integration of other technologies to develop hybrid solutions that leverage multiple power sources. Full article

Fish condition detection, including the identification of feeding desire, biological attachments, fence breaches, and dead fishes, has become an important research frontier in fishery aquaculture. However, perception in underwater conditions is less satisfactory and remains a tricky problem. Firstly, we have developed a multimodal dataset based on Neuromorphic vision (NeuroVI) and RGB images, encompassing challenging fishery aquaculture scenarios. Within the fishery aquaculture dataset, a spike neural network (SNN) method is designed to filter NeuroVI images, and the sift feature points are leveraged to select the optimal image. Next, we propose a dual-image cross-attention learning network that achieves scene segmentation in a fishery aquaculture cage. This network comprises double-channels feature extraction and guided attention learning modules. In detail, the feature matrix of NeuroVI images serves as the query matrix for RGB images, generating attention for calculating key and value matrices. Then, to alleviate the computational burden of the dual-channel network, we replace dot-product multiplication with element-wise multiplication, thereby reducing the computational load among different matrices. Finally, our experimental results from the fishery cage demonstrate that the proposed method achieves the state-of-the-art segmentation performance in the management process of fishery aquaculture. Full article

Underwater imaging is affected by spatially varying blur caused by water flow turbulence, light scattering, and camera motion, resulting in severe visual quality loss and diminished performance in downstream vision tasks. Although numerous underwater image enhancement methods have been proposed, the issue of addressing non-uniform blur under realistic underwater conditions remains largely underexplored. To bridge this gap, we propose PMSPNet, a Progressive Multi-Scale Perception Network, designed to handle underwater non-uniform blur. The network integrates a Hybrid Interaction Attention Module to enable precise modeling of feature ambiguity directions and regional disparities. In addition, a Progressive Motion-Aware Perception Branch is employed to capture spatial orientation variations in blurred regions, progressively refining the localization of blur-related features. A Progressive Feature Feedback Block is incorporated to enhance reconstruction quality by leveraging iterative feature feedback across scales. To facilitate robust evaluation, we construct the Non-uniform Underwater Blur Benchmark, which comprises diverse real-world blur patterns. Extensive experiments on multiple real-world underwater datasets demonstrate that PMSPNet consistently surpasses state-of-the-art methods, achieving on average 25.51 dB PSNR and an inference speed of 0.01 s, which provides high-quality visual perception and downstream application input from underwater sensors for underwater robots, marine ecological monitoring, and inspection tasks. Full article