Search Results (171)

Side-scan sonar (SSS) serves as the primary perceptual instrument for Autonomous Underwater Vehicles (AUVs) in large-scale marine search and rescue (SAR) operations. However, the detection of critical targets is frequently hindered by severe hydro-acoustic noise, the spatial discontinuity of wreckage, and the weak visual signatures of small targets. To surmount these challenges, this paper presents WPG-DetNet. First, we introduce a Wavelet-Embedded Residual Backbone (WERB) to reconstruct the conventional downsampling paradigm. By substituting standard pooling with the Discrete Wavelet Transform (DWT), this architecture explicitly disentangles high-frequency noise from structural information in the frequency domain, thereby achieving the adaptive preservation of edge fidelity for large human-made targets while filtering out speckle interference. Then, addressing the distinct challenge of discontinuous aircraft wreckage, the framework further incorporates a Debris Graph Reasoning Module (D-GRM). This module models scattered fragments as nodes in a topological graph to capture long-range semantic dependencies, transforming isolated instance recognition into context-aware scene understanding. Finally, to bridge the gap between AI and underwater physics, we design a Shadow-Aided Decoupling Head (SADH) equipped with a physics-informed geometric loss. By enforcing mathematical consistency between target height and acoustic shadow length, this mechanism establishes a rigorous discriminative criterion capable of distinguishing weak-echo human bodies from seabed rocks based on shadow geometry. Experiments on the SCTD dataset demonstrate that WPG-DetNet achieves a mean Average Precision ($mA{P}_{50}$) of 97.5% and a Recall of 96.9%. Quantitative analysis reveals that our framework outperforms the classic Faster R-CNN by a margin of 12.8% in $mA{P}_{50}$ and surpasses the Transformer-based RT-DETR-R18 by 5.6% in high-precision localization metrics ($mA{P}_{50:95}$). Simultaneously, WPG-DetNet maintains superior efficiency with an inference speed of 62.5 FPS and a lightweight parameter count of 16.8 M, striking an optimal balance between robust perception and the real-time constraints of AUV operations. Full article

Submarine gas emissions represent a key expression of fluid migration processes in volcanic and hydrothermal marine environments and provide valuable analogues for monitoring strategies relevant to sub-seabed carbon storage. This study investigates the feasibility of using marine Distributed Acoustic Sensing (DAS) to detect natural CO₂ bubble emissions in a shallow-water setting offshore Panarea (Aeolian Islands, Italy). A 1.1 km armored fiber-optic cable was deployed on the seabed and interrogated using two different DAS systems to acquire continuous passive acoustic data. The DAS recordings were complemented by controlled gas releases from scuba tanks to provide reference signals, as well as by independent high-resolution boomer seismic survey and side-scan sonar imaging to characterize the shallow subsurface and seabed morphology. The results show that DAS is sensitive to acoustic signals associated with both artificial and natural bubble emissions, despite the complex acoustic conditions typical of shallow marine environments. The integration of passive DAS monitoring with independent geophysical observations provides a robust framework for interpreting gas-related signals and seabed processes. These findings demonstrate that marine DAS represents a promising geophysical tool for monitoring of submarine volcanic–hydrothermal systems and offers important insights for the development of sub-seabed CO₂ leakage detection in offshore CCS contexts. Full article

Side-scan sonar is essential to underwater target detection, yet its effectiveness is hindered by scarce annotated data and complex acoustic artifacts. This study systematically evaluates four YOLO variants, YOLOv8n, YOLOv10n, YOLOv11n, and the newly released YOLOv13n, on two public side-scan sonar datasets with limited samples and severe class imbalance. We assess detection accuracy, computational efficiency, inference speed, and transfer learning using COCO pre-trained weights, as well as the impact of optimizer choice between SGD and AdamW. The results reveal distinct strengths: YOLOv8n achieves the fastest inference at 60.98 FPS, with a competitive mAP50 of 0.906, ideal for real-time applications. YOLOv11n offers the best accuracy–efficiency balance, attaining the highest recall of 0.859 and mAP50 of 0.917. YOLOv13n demonstrates exceptional precision of 0.993 and high-IoU localization, with an mAP75 of 0.760. Transfer learning consistently boosts performance, with average mAP50:95 gains exceeding 54% on the more challenging dataset, highlighting its critical role in overcoming data scarcity. SGD generally outperforms AdamW, confirming its suitability as the default optimizer. These findings provide practical guidelines: YOLOv8 for real-time needs, YOLOv11 for balanced performance, and YOLOv13 for precision-critical tasks with ample resources. This work also establishes a benchmark for future underwater autonomous system research. Full article

With advancements in Autonomous Underwater Vehicle (AUV) and sensor technologies, the operational paradigms for seabed survey are undergoing significant transformation. Compared to traditional towed or remotely operated platforms, AUV-based seabed survey systems demonstrate superior capabilities in data resolution, operational efficiency and stealth. Furthermore, propelled by progress in artificial intelligence, the technical approaches of AUV-based seabed exploration systems are also experiencing disruptive changes. Based on our observations, existing review articles predominantly focus on individual technologies within seabed survey operations, failing to reflect the systemic constraints and interdependencies among these discrete technological components. This review focuses on the scenario of seabed target detection within seabed survey operations, summarizing research progress aimed at enhancing the effectiveness of such systems across three key technical areas: image processing of side-scan sonar (SSS) systems, intelligent detection of seabed targets and autonomous path planning for survey missions, which is based on a representative system—AUV-mounted SSS system. Given the multi-faceted challenges still present in seabed exploration technology, this paper aims to provide directional guidance for new researchers entering this field. Full article

To enable timely, effective, and high-accuracy detection of scour around offshore wind turbine pile foundations, this study proposes a three-dimensional reconstruction and scour volume detection method based on side-scan sonar imagery. First, the sonar images of pile foundations are preprocessed through grayscale conversion, binarization, and region expansion and merging to obtain an effective grayscale representation of scour pits. An optimized Shape-from-Shading (SFS) method is then applied to reconstruct the three-dimensional geometry from the effective grayscale map, generating point cloud data of the scour pits. Subsequently, the point cloud data are filtered using curvature and normal vector constraints, followed by depth-based z-axis descent detection, clustering, and morphological restoration to extract individual scour pit point clouds. Finally, a weight-corrected AlphaShape algorithm is employed to accurately calculate the volume of each scour pit. Numerical experiments involving five simulated scour scenarios across three types demonstrate that the proposed method achieves accurate identification and extraction of scour pit point clouds, with an average volume measurement accuracy of 97.495% compared with theoretical values. Field measurements in real-world environments further validate the effectiveness of the proposed method for practical scour volume detection around offshore wind turbine foundations. Full article

Automatic Target Recognition (ATR) in single-view sonar imagery is severely hampered by geometric distortions, acoustic shadows, and incomplete target information due to occlusions and the slant-range imaging geometry, which frequently give rise to misclassification and hinder practical underwater detection applications. To address these critical limitations, this paper proposes a Multi-View Deep Convolutional Neural Network (MVDCNN) based on feature-level fusion for robust sonar image target recognition. The MVDCNN adopts a highly modular and extensible architecture consisting of four interconnected modules: an input reshaping module that adapts multi-view images to match the input format of pre-trained backbone networks via dimension merging and channel replication; a shared-weight feature extraction module that leverages Convolutional Neural Network (CNN) or Transformer backbones (e.g., ResNet, Swin Transformer, Vision Transformer) to extract discriminative features from each view, ensuring parameter efficiency and cross-view feature consistency; a feature fusion module that aggregates complementary features (e.g., target texture and shape) across views using max-pooling to retain the most salient characteristics and suppress noisy or occluded view interference; and a lightweight classification module that maps the fused feature representations to target categories. Additionally, to mitigate the data scarcity bottleneck in sonar ATR, we design a multi-view sample augmentation method based on sonar imaging geometric principles: this method systematically combines single-view samples of the same target via the combination formula and screens valid samples within a predefined azimuth range, constructing high-quality multi-view training datasets without relying on complex generative models or massive initial labeled data. Comprehensive evaluations on the Custom Side-Scan Sonar Image Dataset (CSSID) and Nankai Sonar Image Dataset (NKSID) demonstrate the superiority of our framework over single-view baselines. Specifically, the two-view MVDCNN achieves average classification accuracies of 94.72% (CSSID) and 97.24% (NKSID), with relative improvements of 7.93% and 5.05%, respectively; the three-view MVDCNN further boosts the average accuracies to 96.60% and 98.28%. Moreover, MVDCNN substantially elevates the precision and recall of small-sample categories (e.g., Fishing net and Small propeller in NKSID), effectively alleviating the class imbalance challenge. Mechanism validation via t-Distributed Stochastic Neighbor Embedding (t-SNE) feature visualization and prediction confidence distribution analysis confirms that MVDCNN yields more separable feature representations and more confident category predictions, with stronger intra-class compactness and inter-class discrimination in the feature space. The proposed MVDCNN framework provides a robust and interpretable solution for advancing sonar ATR and offers a technical paradigm for multi-view acoustic image understanding in complex underwater environments. Full article

Coralligenous assemblages are among the most diverse habitats of the Mediterranean Sea, yet those of the north-eastern basin remain understudied despite their vulnerability to human impacts and climate change. We applied a multimodal underwater sensing approach to map coralligenous formations, assess gorgonian populations and evaluate the effects of marine litter in a conservation-priority area (NE Aegean Sea, Greece). Side-scan sonar enabled seafloor mapping and guided targeted Remotely Operated Vehicle (ROV) surveys. ROV-based distance sampling and imagery provided quantitative data on Eunicella cavolini and Paramuricea clavata, including density, size structure, and injuries, alongside systematic documentation of marine litter. Gorgonians formed monospecific ecological facies, segregated by location—P. clavata occurred deeper than E. cavolini. Densities were low (E. cavolini: 0.35 colonies m⁻², P. clavata: 1.46 colonies m⁻²) and small colonies (<10 cm) were rare, suggesting limited recruitment. However, the presence of large colonies indicates stable environmental conditions that support long-term persistence, as reproductive output increases with colony size. Colony injuries were minor, but marine litter was abundant, dominated by fishing lines and ropes entangled with gorgonians and sponges. These findings highlight the value of acoustic–optical integration for non-destructive monitoring and provide essential baselines for conservation under EU directives. Full article

Historically, the Mediterranean Sea has been an area of cultural exchange and maritime commerce. One out of many submerged archaeological sites is the Roman shipwreck that was discovered in 2006 off the coast of Santo Stefano al Mare, in the Ligurian Sea, Italy. The wreck was dated to the 1st century B.C. and consists of a well-preserved cargo ship of Roman amphorae that were likely used for transporting wine. In this study, we present the results of the first underwater survey of the wreck using an Autonomous Underwater Vehicle (AUV) industrialized by Graal Tech. The AUV was equipped with a NORBIT WBMS multibeam sonar, a 450 kHz side-scan sonar, and inertial navigation systems. The AUV conducted multiple high-resolution surveys on the wreck site and the collected data were processed using geospatial analysis methods to highlight local anomalies directly related to the presence of the Roman shipwreck. The main feature was an accumulation of amphorae, covering an area of approximately 10 × 7 m with a maximum height of 1 m above the seabed. The results of this interdisciplinary work demonstrated the effectiveness of integrating AUV technologies with spatial analysis techniques for underwater archaeological applications. Furthermore, the success of this mission highlighted the potential for broader applications of AUVs in the study of the seafloor, such as monitoring seabed movements related to offshore underground energy storage or the identification of objects lying on the seabed, such as cables or pipelines. Full article

Amazon River dolphins often form multi-species aggregations at water confluences. This study used a multi-year data set to examine dolphins, fish, and geomorphology at dolphin aggregations. Methods included dolphin transect surveys, dolphin point counts, net and line fish captures, side-scan sonar, and eDNA analyses at five dolphin aggregations and two control sites. Amazon River dolphins (Inia geoffrensis and Sotalia fluviatlis) are typically found at aggregation sites that occur at water confluences that have greater dolphin numbers than control sites. The confluences had riverbed depressions averaging six metres in depth where fish were concentrated. Pink river dolphins preferred to form aggregations in flooded forest tributaries and large rivers, while grey river dolphins preferred the larger rivers. There were eighty-nine fish species at the confluences within the size of fish consumed by dolphins, and a higher abundance of fish occurred in and around the aggregation sites compared to control sites. The number of dolphins present at the aggregation sites correlated with fish abundance. Dolphin life history, such as fishing, resting, raising calves, and social interactions, occur at the aggregation sites. The aggregation sites are important conservation areas of the endangered pink and grey river dolphins, and through their folklore, Indigenous people living at confluence sites assist in the conservation of the aggregations and have lived with dolphins at confluences for thousands of years, contributing to their survival. Full article

As crucial transportation hubs and economic nodes, the underwater security and infrastructure maintenance of harbors are of paramount importance. Harbors are characterized by high vessel traffic and complex underwater environments, where traditional underwater inspection methods, such as diver operations, face challenges of low efficiency, high risk, and limited operational range. This paper introduces a collaborative survey and disposal system that integrates a deformable unmanned surface vehicle (USV) with a lightweight remotely operated vehicle (ROV). The USV is equipped with a side-scan sonar (SSS) and a multibeam echo sounder (MBES), enabling rapid, large-area searches and seabed topographic mapping. The ROV, equipped with an optical camera system, forward-looking sonar (FLS), and a manipulator, is tasked with conducting close-range, detailed observations to confirm and dispose of abnormal objects identified by the USV. Field trials were conducted at an island harbor in the South China Sea, where simulated underwater objects, including an iron drum, a plastic drum, and a rubber tire, were deployed. The results demonstrate that the USV-ROV collaborative system effectively meets the demands for underwater environmental measurement, object localization, identification, and disposal in complex harbor environments. The USV acquired high-resolution (0.5 m × 0.5 m) three-dimensional topographic data of the harbor, effectively revealing its topographical features. The SSS accurately localized and preliminarily identified all deployed simulated objects, revealing their acoustic characteristics. Repeated surveys revealed a maximum positioning deviation of 2.2 m. The lightweight ROV confirmed the status and location of the simulated objects using an optical camera and an underwater positioning system, with a maximum deviation of 3.2 m when compared to the SSS locations. The study highlights the limitations of using either vehicle alone. The USV survey could not precisely confirm the attributes of the objects, whereas a full-area search of 0.36 km² by the ROV alone would take approximately 20 h. In contrast, the USV-ROV collaborative model reduced the total time to detect all objects to 9 h, improving efficiency by 55%. This research offers an efficient, reliable, and economical practical solution for applications such as underwater security, topographic mapping, infrastructure inspection, and channel dredging in harbor environments. Full article

This study addresses the applicability of conventional marine acoustic technologies for detecting non-metal artifacts. Based on the typical environment in Xiamen Bay, we evaluated the detection efficacy of common multibeam sonar, side-scan sonar, and sub-bottom profiling sonar through a controlled model experiment system. We employed ceramic artifact replicas (ranging in size from 10 to 70 cm) and incorporated acoustic parameter optimization to elucidate the applicability boundaries of different technologies. The results indicate that multibeam sonar can identify clustered targets larger than 0.5 m, but is limited in resolving small individual targets (less than 30 cm) due to terrain detail constraints. Side-scan sonar, under low-speed (less than 4 knots) and near-bottom operating conditions, effectively captures the high-intensity echo characteristics of ceramic targets, achieving a maximum effective detection range of more than 40 m. High-frequency sub-bottom profiler (94–110 kHz) offers resolution advantages for exposed artifacts, while low-frequency signals (5–15 kHz) provide theoretical support for detecting subsequently buried targets. Furthermore, the study quantifies the coupling effects of substrate type, target size, and surface roughness on acoustic responses. We propose a synergistic detection workflow comprising “multibeam initial screening—side-scan fine mapping—sub-bottom profiling validation,” which provides empirical support for the optimization and standardization of underwater archeological technologies in complex marine environments. Full article

Eelgrass (Zostera marina) is a native perennial marine angiosperm found in shallow bays and estuaries. Eelgrass beds are considered essential fish habitats and provide an important food source for marine organisms and waterfowl. This study examines changes in extent of the eelgrass beds in the southern portion of the Little Narragansett Bay Estuary, Rhode Island/Connecticut, USA, between 2019 and 2022. The primary dataset used to delineate eelgrass beds was side-scan sonar coupled with underwater video imagery. Previous studies showed a decline in the extent of eelgrass here between 2012 and 2016. Our results show an increase in eelgrass coverage from 0.52 km² in 2019 to 0.75 km² in 2022. This increase in the extent of eelgrass occurred against the trends of declining eelgrass coverage both globally and regionally. Full article

The detection of seabed boulders is a critical step in mitigating geological hazards during the planning and construction of offshore wind energy infrastructure, as well as in supporting benthic ecological and palaeoglaciological studies. Traditionally, side-scan sonar (SSS) has been favoured for such detection, but the growing availability of high-resolution multibeam echosounder (MBES) data offers a cost-effective alternative. This study presents a semi-automated, hybrid GIS-AI approach that combines bathymetric position index filtering and a Random Forest classifier to detect boulders and delineate boulder fields from MBES data. The method was tested on a 0.24 km² site in Long Island Sound using 0.5 m resolution data, achieving 83% recall, 73% precision, and an F1-score of 77—slightly outperforming the average of expert manual picks while offering a substantial improvement in time-efficiency. The workflow was validated against a consensus-based master dataset and applied across a 79 km² study area, identifying over 75,000 contacts and delineating 89 contact clusters. The method enables objective, reproducible, and scalable boulder detection using only MBES data. Its ability to reduce reliance on SSS surveys while maintaining high accuracy and offering workflow customization makes it valuable for geohazard assessment, benthic habitat mapping, and offshore infrastructure planning. Full article

Focusing on the problem of insufficient detection accuracy caused by blurred target boundaries, variable scales, and severe noise interference in side-scan sonar images, this paper proposes a high-precision detection network named ESL-YOLO, which integrates edge perception and adaptive quality assessment. Firstly, an Edge Fusion Module (EFM) is designed, which integrates the Sobel operator into depthwise separable convolution. Through a dual-branch structure, it realizes effective fusion of edge features and spatial features, significantly enhancing the ability to recognize targets with blurred boundaries. Secondly, a Self-Calibrated Dual Attention (SCDA) Module is constructed. By means of feature cross-calibration and multi-scale channel attention fusion mechanisms, it achieves adaptive fusion of shallow details and deep-rooted semantic content, improving the detection accuracy for small-sized targets and targets with elaborate shapes. Finally, a Location Quality Estimator (LQE) is introduced, which quantifies localization quality using the statistical characteristics of bounding box distribution, effectively reducing false detections and missed detections. Experiments on the SIMD dataset show that the mAP@0.5 of ESL-YOLO reaches 84.65%. The precision and recall rate reach 87.67% and 75.63%, respectively. Generalization experiments on additional sonar datasets further validate the effectiveness of the proposed method across different data distributions and target types, providing an effective technical solution for side-scan sonar image target detection. Full article

With the rapid advancement of deep learning techniques, side-scan sonar image segmentation has become a crucial task in underwater scene understanding. However, the complex and variable underwater environment poses significant challenges for salient object detection, with traditional deep learning approaches often suffering from inadequate feature representation and the loss of global context during downsampling, thus compromising the segmentation accuracy of fine structures. To address these issues, we propose SonarNet, a Global Feature-Based Hybrid Attention Network specifically designed for side-scan sonar image segmentation. SonarNet features a dual-encoder architecture that leverages residual blocks and a self-attention mechanism to simultaneously capture both global structural and local contextual information. In addition, an adaptive hybrid attention module is introduced to effectively integrate channel and spatial features, while a global enhancement block fuses multi-scale global and spatial representations from the dual encoders, mitigating information loss throughout the network. Comprehensive experiments on a dedicated underwater sonar dataset demonstrate that SonarNet outperforms ten state-of-the-art saliency detection methods, achieving a mean absolute error as low as 2.35%. These results highlight the superior performance of SonarNet in challenging sonar image segmentation tasks. Full article