IEEE Journal of Oceanic Engineering最新文献

{"title":"HKCoral: Benchmark for Dense Coral Growth Form Segmentation in the Wild","authors":"Ziqiang Zheng;Haixin Liang;Fong Hei Wut;Yue Him Wong;Apple Pui-Yi Chui;Sai-Kit Yeung","doi":"10.1109/JOE.2024.3494112","DOIUrl":"https://doi.org/10.1109/JOE.2024.3494112","url":null,"abstract":"Underwater coral reef monitoring plays an important role in the maintenance and protection of the underwater ecosystem. Extracting information from the collected coral reef images and videos based on computer vision techniques has recently gained increasing attention. Semantic segmentation, which assigns semantic category information to each pixel in images, has been introduced to understand coral reefs. Satisfactory semantic segmentation performance has been achieved based on large-scale in-air data sets with densely labeled annotations. However, underwater coral reef understanding is less explored and existing underwater coral reef data sets are mainly captured under <italic>ideal</i> and <italic>normal</i> conditions and lack variance. They cannot fully reflect the diversity and properties of coral reefs. Thus, trained coral reef segmentation models show very limited performance when deployed in <italic>practical</i>, <italic>challenging</i>, and <italic>adverse</i> conditions. To address these issues, in this article, we propose an <italic>in-the-wild</i> coral reef data set named <italic>HKCoral</i> to close the gap for performing in-situ coral reef monitoring. The collected data set with dense pixel-wise annotations possesses larger diversity, appearance, viewpoint, and visibility variations. Besides, we adopt the fundamental coral <italic>growth form</i> as the foundation of our semantic coral reef segmentation, which enables a strong generalizability to unseen coral reef images from different sites. We benchmark the coral reef segmentation performance of 17 state-of-the-art semantic segmentation algorithms (including the recent generalist segment anything model) and further introduce a complementary architecture to better utilize underwater image enhancement for improving the segmentation performance of models. We have conducted extensive experiments based on various up-to-date segmentation models on our benchmark and the experimental results demonstrate that there is still ample room to improve coral segmentation performance. Ablation studies and discussions are also included. The proposed benchmark could significantly enhance the efficiency and accuracy of real-world underwater coral reef surveying.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"697-713"},"PeriodicalIF":3.8,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10904825","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852416","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}

{"title":"CE$^{3}$USOD: Channel-Enhanced, Efficient, and Effective Network for Underwater Salient Object Detection","authors":"Qingyao Wu;Jiaxin Xie;Zhenqi Fu;Xiaotong Tu;Yue Huang;Xinghao Ding","doi":"10.1109/JOE.2024.3523356","DOIUrl":"https://doi.org/10.1109/JOE.2024.3523356","url":null,"abstract":"Underwater salient object detection (USOD) aims to identify the most crucial elements in underwater environments, holding significant potential for underwater exploration. Existing methods often overlook light degradation or involve larger network sizes, which are unsuitable for underwater mobile platforms and pose challenges to implement in practice. Given the importance of low-complexity algorithms in underwater applications to optimize system efficiency, this article introduces CE<inline-formula><tex-math>$^{3}$</tex-math> </inline-formula>USOD—an efficient network tailored to deliver an effective solution for salient object detection in underwater scenarios. On the one hand, we reconsider long-range dependencies and feature computation from a neighborhood perspective, leading to the development of the long-range context-aware module. Specifically, we approximate local and global context awareness by incorporating the maximum and average values of neighboring pixels within varying window sizes, which allows our method to achieve high performance while maintaining low computational cost. On the other hand, light scattering and absorption during underwater imaging frequently result in channel intensity imbalances in captured underwater images. To address this, we propose the color-guided pyramid aggregation module, which utilizes the weaker color channels enhanced by underwater image enhancement techniques as guiders for multiscale feature fusion, finally facilitating the model to obtain underwater domain information. Extensive experiments on four public benchmarks demonstrate that our innovative network achieves state-of-the-art results while maintaining a low model size (Params of 0.546M) and computational complexity (FLOPs of 0.416G). Therefore, CE<inline-formula><tex-math>$^{3}$</tex-math> </inline-formula>USOD proves to be effective and efficient, establishing its practicality, particularly for underwater applications.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"941-954"},"PeriodicalIF":3.8,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848872","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}

{"title":"Design, Development, and Testing of an Innovative Autonomous Underwater Reconfigurable Vehicle for Versatile Applications","authors":"Mirco Vangi;Edoardo Topini;Gherardo Liverani;Alberto Topini;Alessandro Ridolfi;Benedetto Allotta","doi":"10.1109/JOE.2024.3511709","DOIUrl":"https://doi.org/10.1109/JOE.2024.3511709","url":null,"abstract":"The underwater industry and scientific community are actively researching the development of vehicles that combine the functionalities of autonomous underwater vehicles and remotely operated vehicles. An innovative approach to address the challenges posed by underwater exploration is the development of autonomous underwater reconfigurable vehicles (AURVs). These vehicles are designed to adapt their configuration to suit the requirements of the task at hand. The flexibility of AURVs enables them to undertake a variety of underwater missions, ranging from scientific research to deep-sea exploration. The Department of Industrial Engineering at the University of Florence, Italy, has developed and patented an innovative AURV that is able to quickly change its shape to suit different tasks. The reconfigurable underwater vehicle for inspection, free-floating intervention and survey tasks (RUVIFIST) have been equipped with two extreme configurations. The first configuration is a slender one meant for long navigation tasks, while the second configuration is a stocky one designed for tackling complex objectives such as inspection or intervention operations. With the ability to adapt its form to suit the task at hand, the RUVIFIST vehicle represents a significant advancement in underwater vehicle technology. This work provides an overview of the challenges faced and the solutions adopted during the development of this new vehicle. This article presents the results of experimental campaigns to test the reconfigurable system of the vehicle and the strategies developed for the guidance, navigation, and control system of AURVs. Finally, preliminary tests were conducted to explore the integration of machine learning and deep learning algorithms that are compatible with the purpose of automatic target recognition.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"509-526"},"PeriodicalIF":3.8,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10904475","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852373","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}

{"title":"Adaptive Refocusing Chain for Moving Ships in Satellite SAR Images","authors":"Seung-Jae Lee","doi":"10.1109/JOE.2025.3529210","DOIUrl":"https://doi.org/10.1109/JOE.2025.3529210","url":null,"abstract":"In this study, an adaptive refocusing scheme for moving ships in satellite synthetic aperture radar (SAR) images is proposed to cope with various types of motions of ship targets. To decide the type of ship's motion, the phase signals of principal scatterers are analyzed based on the inverse SAR (ISAR) signal model with the help of a joint time–frequency transform and deep learning model. Then, proper ISAR-based refocusing algorithms are used to generate a well-focused image considering the ship's motion. The design of the adaptive refocusing concept enables us to select appropriate algorithms to retrieve the exact scattering mechanisms of ship targets. In addition, to cope with defocusing due to the complex 3-D motion of the ship, an efficient reconstruction strategy based on compressive sensing is devised. It is a concept different from conventional optimal time windowing, which deals with the complex motion of the ship target, and it yields a well-focused image that retains the spatial resolution of the original ship image. In experiments using simulated and real SAR images, the proposed method shows reliable refocusing results for various ship targets compared to traditional methods.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"1290-1308"},"PeriodicalIF":3.8,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10904822","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852451","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}

{"title":"Line-of-Sight Guidance: Learning to Look Ahead","authors":"Eirik Lothe Foseid;Erlend Andreas Basso;Henrik M. Schmidt-Didlaukies;Kristin Ytterstad Pettersen;Jan Tommy Gravdahl","doi":"10.1109/JOE.2024.3503765","DOIUrl":"https://doi.org/10.1109/JOE.2024.3503765","url":null,"abstract":"This article introduces a novel line-of-sight (LOS) guidance approach utilizing a neural network to parameterize the lookahead distance. We prove that the proposed guidance law renders a compact set containing the origin uniformly globally asymptotically stable (UGAS) for the closed-loop system. Importantly, if the sideways velocity is zero, the proposed guidance law renders the origin of the closed-loop system UGAS. By employing a neural network to parameterize the lookahead distance, the learning process results in a locally optimal lookahead distance for a given performance metric, and allows for nonlinear variation of the lookahead distance based on arbitrary input. We demonstrate how the proposed approach outperforms several state-of-the-art LOS guidance schemes utilizing time-varying lookahead distances.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1637-1646"},"PeriodicalIF":3.8,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646560","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}

{"title":"Hilbert–Huang Transform With Intelligent Noise Reduction for Passive SONAR Signal Processing","authors":"Elio Pithon Sarno Filho;Anderson Damacena Santos;Eduardo F. Simas Filho;Antonio Carlos Lopes Fernandes;José Manoel de Seixas;Natanael N. de Moura","doi":"10.1109/JOE.2024.3519737","DOIUrl":"https://doi.org/10.1109/JOE.2024.3519737","url":null,"abstract":"Ocean science plays a key role in marine exploration, encouraging the development of new methods for analyzing underwater acoustic waves. In passive SOund NAvigation and Ranging (SONAR) signal processing for military vessel detection and classification, the predominant technique is the short-time Fourier transform (STFT). However, this spectral analysis method has time–frequency (TF) resolution limitations, impacting performance in feature extraction and vessel dynamic behavior monitoring. The Hilbert–Huang transform (HHT) is an alternative to STFT, providing a data-driven TF analysis with high resolution. However, in standard HHT algorithms, estimation accuracy degrades as noise increases. This article presents a novel algorithm for HHT that computes the HHT with intelligent noise removal (HHT-INR). The proposed method is focused on passive SONAR surveillance applications, in which the information of interest usually comprises different sinusoidal components produced by the vessels' machinery and propeller system. An intelligent system based on support vector machine detects and removes noisy IMF during the EMD estimation process. Results with simulated and experimental passive SONAR signals indicate better performance than the STFT-based analysis. The HHT-INR reduces background noise and enhances resolution for analyzing vessel parameters in time-varying scenarios. The proposed method significantly improved frequency resolution in experimental signals, achieving an average reduction in spectral width of approximately 28.5 times. In addition, there was an average increase of 87.9 dB in the signal-to-noise ratio.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"1387-1402"},"PeriodicalIF":3.8,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10899432","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860763","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}

{"title":"Sea Surface Wave Retrieval From C-Band Sentinel-1 Images in the Arctic Ocean","authors":"Yuyi Hu;Weizeng Shao;Maurizio Migliaccio;Ferdinando Nunziata;Qingjun Zhang","doi":"10.1109/JOE.2024.3519738","DOIUrl":"https://doi.org/10.1109/JOE.2024.3519738","url":null,"abstract":"The Arctic Ocean presents significant challenges for estimating sea surface wave fields using <italic>C</i>-band synthetic aperture radar (SAR) due to the distortion caused by the reflection of sea ice. This article introduces a novel procedure to successfully consider the influence of sea ice in SAR wave retrieval at latitude <80°.>K</i>-means clustering algorithm was applied to estimate sea ice concentration from the images. Using 1000 images in the training data set, the tilt mapping model transfer functions (MTFs) in VV and HH polarization are generated under various sea ice concentration conditions. Then, a theoretical wave retrieval algorithm, namely, the parameterized first-guess spectrum method, that uses the updated tilt MTF was implemented for an additional 600 images in a test data set for wave retrieval in the Arctic Ocean. Compression of the SAR-derived SWHs and WW3 simulations yields an RMSE of 0.45 m, a COR of 0.91, a bias of 0.38 m, and an SI of 0.11 using the updated tilt MTF, which is an improvement upon the RMSE of 0.60 m, a bias of 0.41 m, a COR of 0.88, and an SI of 0.14 obtained using the previous tilt MTF. Moreover, the accuracy of VV-polarized SAR-derived SWH by using the updated tilt MTF is improved by approximately 0.15-m RMSE and 0.08-m bias, which is based on validating SAR-derived SWHs against the measurements from the HY-2B altimeter. However, the noise in the retrievals still needs further mitigation.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"1259-1272"},"PeriodicalIF":3.8,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852464","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}

{"title":"Adaptive Hand Position for Underactuated Underwater Vehicles","authors":"Josef Matouš;Kristin Y. Pettersen;Damiano Varagnolo;Claudio Paliotta;Else-Line Ruud","doi":"10.1109/JOE.2024.3511708","DOIUrl":"https://doi.org/10.1109/JOE.2024.3511708","url":null,"abstract":"The hand position is a virtual point on a vehicle, located at a specific distance in front of its center of mass. This concept is a simple yet effective method that can be used for the stabilization and control of a wide range of systems, including nonholonomic vehicles (e.g., differential drive robots) and underactuated vehicles (e.g., certain types of autonomous surface and underwater vehicles). In previous works on underactuated vehicles, the hand position was fixed (i.e., constant). In this article, we introduce the concept of an adaptive (time-varying) hand position to underactuated underwater vehicles and demonstrate its effectiveness on the 3-D trajectory-tracking problem. To do so, we first define the transformation from the vehicle's coordinate system to the hand position coordinates. Then, we use the adaptive hand position concept to design a trajectory-tracking controller with saturations. We use Lyapunov methods to prove that the controller renders the system uniformly globally asymptotically stable. The theoretical results are verified in numerical simulations.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1647-1656"},"PeriodicalIF":3.8,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646413","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}

{"title":"CA-Net: Cascaded Adaptive Network for Underwater Image Enhancement","authors":"Xiaofei Zhou;Ming Peng;Qiuping Jiang;Runmin Cong;Jiyong Wang;Yun Chen","doi":"10.1109/JOE.2024.3501399","DOIUrl":"https://doi.org/10.1109/JOE.2024.3501399","url":null,"abstract":"Due to light absorption and scattering, underwater images often suffer from low contrast, blurry details, and color deviation. Various enhancement methods have been developed, but many fail to improve image quality effectively and sometimes create unnatural effects. To tackle such a problem, we propose a novel method, namely the Cascaded Adaptive Network (i.e., CA-Net), to comprehensively enhance the quality of underwater images. Specifically, our network adopts a cascaded enhancement architecture consisting of three stages (coarse feature restoration, feature aggregation, and color refinement). First, we use a detail restoration (DR) module and channel balance module to recover spatial details and correct color distortion, respectively, in the first stage. Particularly, the detail guidance unit of DR employs encoder features to steer the decoder features to focus more on the spatial details of objects. Second, to promote the fusion of fine details and color features, we deploy a context attention (CA) module and an adaptive feature fusion (AFF) module in the stage of feature aggregation. CA extracts detailed restoration features and long-range dependencies in images, guiding the fusion process in the subsequent AFF. Lastly, to guarantee natural colors, we use a global color rendering module in the stage of color refinement, which adaptively groups and tunes the image channels. Experiments on public data sets show that CA-Net significantly outperforms existing methods, making it highly effective for underwater image enhancement.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"879-897"},"PeriodicalIF":3.8,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848832","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}

{"title":"UIEFormer: Lightweight Vision Transformer for Underwater Image Enhancement","authors":"Juntian Qu;Xiangyu Cao;Shancheng Jiang;Jia You;Zhenping Yu","doi":"10.1109/JOE.2024.3519681","DOIUrl":"https://doi.org/10.1109/JOE.2024.3519681","url":null,"abstract":"The selective absorption and scattering of light in water degrade underwater image quality, hindering the performance of underwater tasks. Moreover, existing data-driven underwater image enhancement (UIE) methods rely on large-scale, high-quality underwater image data sets, which are costly to acquire in terms of time and labor. In this work, we present a UIE framework named UIEFormer, which is built upon a popular conventional image defogging framework DehazeFormer, possessing satisfactory performance on a small-scale training data set of underwater images. We propose an interpolation-based upsampling strategy to avoid checkerboard artifacts caused by PixelShuffle. Extra feature channels are introduced to segregate noncritical high-level image features for UIE tasks. Further, we apply a loss function combining per-pixel loss, perceptual loss, and coloration loss to adapt to the underwater environment. Results on real-world data sets demonstrate that our method has certain advantages over classical and popular UIE methods. In addition, we conduct ablation experiments to demonstrate the contribution of each module in our work. We also demonstrate the practical significance of our approach for underwater image processing tasks.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"851-865"},"PeriodicalIF":3.8,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848784","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}