IEEE Journal of Oceanic Engineering最新文献_第4页

LUSSNet: A Lightweight Underwater Semantic Segmentation Network for Efficient Aquaculture Perception 用于水产养殖高效感知的轻量级水下语义分割网络

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-06-30 DOI: 10.1109/JOE.2026.3697992

Zhiqian He;Yajun Chen;Lijie Cao

{"title":"LUSSNet: A Lightweight Underwater Semantic Segmentation Network for Efficient Aquaculture Perception","authors":"Zhiqian He;Yajun Chen;Lijie Cao","doi":"10.1109/JOE.2026.3697992","DOIUrl":"https://doi.org/10.1109/JOE.2026.3697992","url":null,"abstract":"Underwater image semantic segmentation is an important pixel-level perception task in intelligent aquaculture, supporting organism localization, growth estimation, behavior analysis, and scene monitoring. However, underwater aquaculture images are often degraded by light attenuation, scattering, color distortion, low contrast, suspended particles, and blurred object boundaries. These factors make it difficult for lightweight segmentation models to preserve discriminative spatial details while maintaining efficient inference. To address this problem, this article proposes a lightweight underwater semantic segmentation network, termed LUSSNet, to achieve a favorable balance between segmentation accuracy and computational efficiency under degraded underwater imaging conditions. First, a fine-grained multilevel feature attention module is designed to enhance shallow feature representation through multiscale receptive fields and spatial-channel attention. This module helps retain texture and boundary cues for low-contrast and blurred underwater targets without relying on a heavy backbone. Second, an adaptive feature fusion module (AFFM) is introduced for structure-preserving multilevel feature fusion. By combining wavelet-based downsampling with adaptive feature adjustment, AFFM helps preserve edge-related spatial information and suppress redundant channel responses during feature aggregation. Third, a Wasserstein distance dice loss is proposed and combined with focal loss to improve optimization stability for small foreground objects and imbalanced regions. Experiments on the SUIM and DUT-USEG data sets show that LUSSNet achieves 60.16% and 53.09% mIoU, respectively. The model contains 3.82 M parameters, requires 26.36 GFLOPs, and reaches 59.88 FPS under the same evaluation setting. These results demonstrate that LUSSNet achieves a competitive accuracy-efficiency trade-off for lightweight underwater semantic segmentation.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"51 3","pages":"2532-2544"},"PeriodicalIF":5.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive Spectral Line Enhancement Using Deep Feature Extraction Guided FISTA-Net for Noise-Resilient Underwater Passive Sonar Detection and Classification 基于深度特征提取的FISTA-Net自适应谱线增强水下被动声纳检测与分类

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-04-09 DOI: 10.1109/JOE.2026.3675821

Riya Rani S S;Sumit Datta

{"title":"Adaptive Spectral Line Enhancement Using Deep Feature Extraction Guided FISTA-Net for Noise-Resilient Underwater Passive Sonar Detection and Classification","authors":"Riya Rani S S;Sumit Datta","doi":"10.1109/JOE.2026.3675821","DOIUrl":"https://doi.org/10.1109/JOE.2026.3675821","url":null,"abstract":"The low frequency analysis and recording (LOFAR) spectrum plays a vital role in underwater passive sonar target detection. High noise levels in the marine environment degrade the quality of spectral lines in LOFAR spectrograms and hinder target detection. This article proposes a novel hybrid approach for LOFAR spectrum enhancement that integrates a sparse optimization algorithm and a deep learning approach for adaptive, noise resilient spectral line preservation. The proposed architecture employs U-shaped network (U-Net) as a spectral line selector and a cascaded fast iterative shrinkage-thresholding algorithm (FISTA) network for adaptive noise suppression. The U-Net selectively emphasizes salient frequency components, guiding the subsequent FISTA blocks to perform enhancement while preserving critical spectral lines. A signal-to-noise ratio (SNR) estimation module dynamically evaluates the noise level and adaptively determines the appropriate denoising level, enabling precise noise suppression. Experimental results using ShipsEar data sets demonstrate that the proposed method, namely, deep feature extraction guided FISTA-Net achieves an SNR gain of 3.37 dB over the state-of-the-art method, namely, fast block processed sparsity adaptive line enhancer (ALE) and 7.12 dB over sparsity induced ALE. In addition to the SNR improvement, the proposed method achieves an average signal-to-distortion ratio of 21.64 dB, which is 2.67 dB higher than the best performing existing method, further confirming its effectiveness in preserving signal quality while suppressing noise. For the evaluation of classification performance, a common residual neural network classifier was employed across all methods. The proposed approach achieves a classification accuracy of 96.95%, outperforming existing state-of-the-art techniques, confirming the proposed method's effectiveness in enhancing the detection and recognition of underwater acoustic targets.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"51 3","pages":"2274-2283"},"PeriodicalIF":5.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Filtered Backstepping-Based Robust Trajectory Tracking Control of Marine Surface Vessels Under Mismatched Disturbances With Fixed-Time Disturbance Observers 非匹配扰动下带固定时间扰动观测器的滤波后阶鲁棒跟踪控制

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-06-03 DOI: 10.1109/JOE.2026.3687159

Jingqi Zhang;Shuanghe Yu

引用次数: 0

PLUM: A Prompt-Guided Lightweight Unified Model for Enhancement of Multidegraded Underwater Image 多退化水下图像增强的快速引导轻量级统一模型

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-03-06 DOI: 10.1109/JOE.2026.3680311

Alik Pramanick;Akshay Daydar;Sonal Kumar;Arijit Sur;V. Vijaya Saradhi

{"title":"PLUM: A Prompt-Guided Lightweight Unified Model for Enhancement of Multidegraded Underwater Image","authors":"Alik Pramanick;Akshay Daydar;Sonal Kumar;Arijit Sur;V. Vijaya Saradhi","doi":"10.1109/JOE.2026.3680311","DOIUrl":"https://doi.org/10.1109/JOE.2026.3680311","url":null,"abstract":"Degradation in underwater images is commonly caused by haze, low contrast, blur, and color distortion, which can hinder the effectiveness of many computer vision tasks. Most of the existing image enhancement works treat these degradations separately, thus limiting their applicability. To handle this problem, we propose a unified model to learn multiple degradations concurrently, improving resilience to practical conditions. First, we generate various degraded versions (haze, blur, low-contrast, and color distortion) of the input degraded image through domain translation. Next, original degraded and translated images are fed into a novel multidegraded enhancement network, which employs multiple encoders with an intermediate feature-swapping mechanism and a single decoder. Each encoder block enhances the network’s ability to characterize internal relationships in spatial and frequency domains by incorporating the fast Fourier transform. Intermediate feature swapping encourages the model to learn more robust representations. The decoder block contains the proposed prompt-guided spatial-frequency cross-attention block to encode degraded visual information effectively. Extensive experiments on several underwater image enhancement data sets demonstrate that our model outperforms the state-of-the-art methods with less computational cost (e.g., 1.20% structural similarity index boost on UIEB data set with 84.1% less parameter).","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"51 3","pages":"2516-2531"},"PeriodicalIF":5.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148452018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Field Evaluation of a MEMS-Based Silicon Resonant Pressure Sensor for Seafloor Pressure Observation 用于海底压力观测的mems硅谐振压力传感器的现场评估

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-06-05 DOI: 10.1109/JOE.2026.3674030

Masanao Shinohara;Takashi Kunugi;Shin Aoi;Shigeto Iwai;Takashi Yoshida;Toshihiko Oomachi;Ryuichiro Noda;Tetsuya Takeda;Masashi Mochizuki;Kenji Uehira;Tomoaki Yamada

{"title":"Field Evaluation of a MEMS-Based Silicon Resonant Pressure Sensor for Seafloor Pressure Observation","authors":"Masanao Shinohara;Takashi Kunugi;Shin Aoi;Shigeto Iwai;Takashi Yoshida;Toshihiko Oomachi;Ryuichiro Noda;Tetsuya Takeda;Masashi Mochizuki;Kenji Uehira;Tomoaki Yamada","doi":"10.1109/JOE.2026.3674030","DOIUrl":"https://doi.org/10.1109/JOE.2026.3674030","url":null,"abstract":"Seafloor pressure observations mainly use precise quartz resonant sensors at present due to their high sensitivity. Recently, a new silicon resonant sensor using microelectromechanical systems (MEMS) technology has emerged with low-power consumption, compact size, constant quality, and high sensitivity. High stability is expected due to the small size of a silicon resonant pressure sensor, and interunit variability among sensors is believed to be small because of the MEMS technology. The influence of the movement of the sensor itself is small due to the mechanism of pressure transmission. Nankai Trough seafloor observation network for earthquakes and tsunamis, named N-net, is equipped with the new sensors. Before routine observations using this new sensor, we evaluate the performance of the new silicon resonant sensor for seafloor pressure observation. An existing free-fall pop-up type ocean bottom pressure gauge has a quartz crystal resonant sensor. We replaced the sensor with the new silicon resonant pressure sensor and performed seafloor observations off the Boso peninsula near Tokyo. We obtained pressure data from two new sensors. Noise spectra of the new sensor were compared to those of the ordinary crystal sensor, which was installed at the same position. The new and ordinary gauges have identical noise levels at periods longer than about 50 s. Although the new silicon gauges seem to have slightly higher noise levels at periods between 50 and 10 s, the new pressure gauge can detect pressure changes larger than 1 hPa throughout the whole observation band. The new pressure gauge observed sea level fluctuation by volcanic eruption in Tonga and the identical waveforms were obtained from the new and ordinary pressure gauges.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"51 3","pages":"2137-2146"},"PeriodicalIF":5.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11552632","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Collision-Free Fixed-Time Distributed Formation-Containment Control for Underactuated USVs With Unmodeled Dynamics and Input Constraints 具有未建模动力学和输入约束的欠驱动usv无碰撞固定时间分布式编队控制

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-03-05 DOI: 10.1109/JOE.2026.3674031

Junpeng Li;Yunsheng Fan;Hui Sun;Guibing Zhu;Chenlei Wang

{"title":"Collision-Free Fixed-Time Distributed Formation-Containment Control for Underactuated USVs With Unmodeled Dynamics and Input Constraints","authors":"Junpeng Li;Yunsheng Fan;Hui Sun;Guibing Zhu;Chenlei Wang","doi":"10.1109/JOE.2026.3674031","DOIUrl":"https://doi.org/10.1109/JOE.2026.3674031","url":null,"abstract":"In this article, a fixed-time formation-containment control approach is developed for coordinating multiple underactuated unmanned surface vehicles (USVs) subject to unmodeled dynamics and input constraints. First, a coordinate transformation is introduced to address the underactuated dynamics of each USV. Then, compound uncertainties are estimated by employing a fixed-time disturbance observer based on input–output data. To enhance formation safety, an artificial potential function is utilized to facilitate collision avoidance and maintain safe distances among USVs. The real-time derivatives of the virtual control laws are computed using a fixed-time differentiator, which facilitates a simplified controller structure. An asymmetric differentiable saturation function is utilized to construct a distributed formation-containment controller, while an auxiliary system is introduced to compensate for input constraints. Under this control scheme, all follower USVs are guaranteed to reach and stay within the convex hull spanned by multiple reference leaders in fixed time, thus achieving the desired formation-containment objective. The fixed-time stability of the entire closed-loop system is rigorously established via Lyapunov theory. Simulation results verify the effectiveness, safety, and superiority of the proposed control approach.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"51 3","pages":"1817-1832"},"PeriodicalIF":5.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LUSSNet: A Lightweight Underwater Semantic Segmentation Network for Efficient Aquaculture Perception 用于水产养殖高效感知的轻量级水下语义分割网络

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-06-30 DOI: 10.1109/JOE.2026.3697992

Zhiqian He;Yajun Chen;Lijie Cao

{"title":"LUSSNet: A Lightweight Underwater Semantic Segmentation Network for Efficient Aquaculture Perception","authors":"Zhiqian He;Yajun Chen;Lijie Cao","doi":"10.1109/JOE.2026.3697992","DOIUrl":"https://doi.org/10.1109/JOE.2026.3697992","url":null,"abstract":"Underwater image semantic segmentation is an important pixel-level perception task in intelligent aquaculture, supporting organism localization, growth estimation, behavior analysis, and scene monitoring. However, underwater aquaculture images are often degraded by light attenuation, scattering, color distortion, low contrast, suspended particles, and blurred object boundaries. These factors make it difficult for lightweight segmentation models to preserve discriminative spatial details while maintaining efficient inference. To address this problem, this article proposes a lightweight underwater semantic segmentation network, termed LUSSNet, to achieve a favorable balance between segmentation accuracy and computational efficiency under degraded underwater imaging conditions. First, a fine-grained multilevel feature attention module is designed to enhance shallow feature representation through multiscale receptive fields and spatial-channel attention. This module helps retain texture and boundary cues for low-contrast and blurred underwater targets without relying on a heavy backbone. Second, an adaptive feature fusion module (AFFM) is introduced for structure-preserving multilevel feature fusion. By combining wavelet-based downsampling with adaptive feature adjustment, AFFM helps preserve edge-related spatial information and suppress redundant channel responses during feature aggregation. Third, a Wasserstein distance dice loss is proposed and combined with focal loss to improve optimization stability for small foreground objects and imbalanced regions. Experiments on the SUIM and DUT-USEG data sets show that LUSSNet achieves 60.16% and 53.09% mIoU, respectively. The model contains 3.82 M parameters, requires 26.36 GFLOPs, and reaches 59.88 FPS under the same evaluation setting. These results demonstrate that LUSSNet achieves a competitive accuracy-efficiency trade-off for lightweight underwater semantic segmentation.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"51 3","pages":"2532-2544"},"PeriodicalIF":5.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MORSE: A Rapid Marine Organism Observation Framework via Sonar Point Map 基于声纳点图的海洋生物快速观测框架

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-06-26 DOI: 10.1109/JOE.2026.3697319

Yuanju Cao;Caoyang Yu;Chao Xu;Xianbo Xiang;Lian Lian

{"title":"MORSE: A Rapid Marine Organism Observation Framework via Sonar Point Map","authors":"Yuanju Cao;Caoyang Yu;Chao Xu;Xianbo Xiang;Lian Lian","doi":"10.1109/JOE.2026.3697319","DOIUrl":"https://doi.org/10.1109/JOE.2026.3697319","url":null,"abstract":"To enhance the observation of marine organisms in complex underwater environments, this article presents an innovative noninvasive monitoring approach that processes raw water-column signals from forward-looking sonar (FLS) into a sonar point map. This method supports the investigation of high-frequency acoustic characteristics of marine organisms. A bio-acoustic scattering model for FLS is first established to analyze the relationship between sonar point map and the acoustic features of biological targets. Particular attention is given to echo intensity information, which is often neglected in traditional image-based observation techniques. To improve the reliability of intensity-based analysis, practical calibration is introduced through distance-intensity compensation. To address the challenges posed by acoustic reverberation and noise, an adaptive region growing scheme is proposed to capture multiple features of the target region from sonar point map. These processes are integrated into a comprehensive framework named marine organism rapid sonar point map exploration (MORSE), which combines Bayesian probabilistic classification with machine learning techniques to enable rapid target identification. MORSE also incorporates an improved particle filter algorithm to support continuous target tracking. Experiments on four representative marine species, including fishes, turtle, and scallop, confirm that the MORSE framework achieves comparable classification performance to image-based lightweight neural networks, while requiring fewer computational resources and providing stronger consistency with acoustic scattering models. In tracking tasks, MORSE achieves an average accuracy exceeding 95% and maintains a global positional error below 10 cm.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"51 3","pages":"2222-2241"},"PeriodicalIF":5.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Three-Dimensional Ocean Wave Motion-Induced Electromagnetic Fields and Seafloor Measurements 三维海浪运动感应电磁场和海底测量

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-06-23 DOI: 10.1109/JOE.2026.3693814

Lindong Pan;Yuguo Li

{"title":"Three-Dimensional Ocean Wave Motion-Induced Electromagnetic Fields and Seafloor Measurements","authors":"Lindong Pan;Yuguo Li","doi":"10.1109/JOE.2026.3693814","DOIUrl":"https://doi.org/10.1109/JOE.2026.3693814","url":null,"abstract":"The theory of electromagnetic (EM) fields induced by ocean wave motion (OWEM) has been mainly 2-D since the 1960s. This restricts the development of marine EM detection technology. In this article, we begin with the complete Maxwell partial differential equations, derive the expressions for the 3-D OWEM fields under the horizontal <italic>N</i>-layered model, and compile the program (fOWEMF-3D). We verified the correctness of our algorithm’s response by comparing it with previous classic algorithms. Furthermore, we conducted a marine EM survey in a shallow seawater area. A horizontally layered geoelectric model closely resembling a real situation was constructed based on the conductivity data from seafloor drilling. The 3-D OWEM response was calculated using surface wave height data measured by a seafloor sensor and ocean wave propagation direction data from European Centre for Medium-Range Weather Forecasts (ECMWF), and compared with ocean bottom EM (OBEM) data that is least disturbed by vibration EM interference, thereby verifying the effectiveness of the algorithm. Ultimately, the OWEM field algorithm was successfully extended from 2-D to 3-D. The solution to this problem has implications for OWEM noise suppression, the inversion of kinematic parameters using OEWM data, and other applications.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"51 3","pages":"1705-1717"},"PeriodicalIF":5.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Image Compression Using Novel View Synthesis Priors 使用新的视图合成先验的图像压缩

IF 5.6 2区工程技术

IEEE Journal of Oceanic Engineering Pub Date : 2026-07-01 Epub Date: 2026-03-05 DOI: 10.1109/JOE.2026.3674685

Luyuan Peng;Mandar Chitre;Hari Vishnu;Yuen Min Too;Bharath Kalyan;Rajat Mishra;Soo Pieng Tan

{"title":"Image Compression Using Novel View Synthesis Priors","authors":"Luyuan Peng;Mandar Chitre;Hari Vishnu;Yuen Min Too;Bharath Kalyan;Rajat Mishra;Soo Pieng Tan","doi":"10.1109/JOE.2026.3674685","DOIUrl":"https://doi.org/10.1109/JOE.2026.3674685","url":null,"abstract":"Real-time visual feedback is essential for tetherless control of remotely operated vehicles, particularly during inspection and manipulation tasks. Though acoustic communication is the preferred choice for medium-range communication underwater, its limited bandwidth renders it impractical to transmit images or videos in realtime. To address this, we propose a model-based image compression technique that leverages prior mission information. Our approach employs trained machine-learning based novel view synthesis models to store and render views of scenes that serve as priors, and minimizes the differences between camera images and model-rendered images to improve compressibility. We evaluate our method using data sets collected in an artificial ocean basin and demonstrate significant improvements in compression ratio and image quality compared to existing methods. Moreover, our approach exhibits robustness to the introduction of novel objects within the basin scene and maintains performance under real-world degradations, such as backscatter, as demonstrated on an online coral reef data set. These results highlight the promise of our proposed technique for enabling real-time, high-quality visual feedback over bandwidth-constrained underwater acoustic links.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"51 3","pages":"1689-1704"},"PeriodicalIF":5.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0