A synthetic aperture radar (SAR) is used to persistently monitor marine areas in all-weather conditions for excellent ship and wake identification. Current deep-learning-based ship wake detection methods rely on supervised learning. However, no publicly available large-scale SAR dataset is available to support this learning method. Owing to the diversity of ship wake characteristics in SAR images and the complexities of sea states, contemporary computer vision algorithms are generally ineffective for SAR image recognition tasks. To overcome these issues, this letter presents the new, well-annotated OpenSARWake dataset dedicated to oriented ship wake detection. This collection provides 3973 images containing two polarization modes and 4096 instances. Their image features are used to train a novel two-stage SWNet feature refinement detector that adopts a sophisticated HR-FPN* backbone for SAR ship wake detection. The detector recognizes nearly all wake characterizations. The trained SWNet achieves state-of-the-art detection performance with 49.0% mAP, outperforming most benchmarking algorithms. The OpenSARWake dataset is available at https://github.com/libzzluo/OpenSARWake .

Computer vision systems are insensitive to the scale of objects in natural scenes, so it is important to study the multi-scale representation of features. Res2Net implements hierarchical multi-scale convolution in residual blocks, but its random grouping method affects the robustness and intuitive interpretability of the network. We propose a new multi-scale convolution model based on multiple attention. It introduces the attention mechanism into the structure of a Res2-block to better guide feature expression. First, we adopt channel attention to score channels and sort them in descending order of the feature’s importance (Channels-Sort). The sorted residual blocks are grouped and intra-block hierarchically convolved to form a single attention and multi-scale block (AMS-block). Then, we implement channel attention on the residual small blocks to constitute a dual attention and multi-scale block (DAMS-block). Introducing spatial attention before sorting the channels to form multi-attention multi-scale blocks(MAMS-block). A MAMS-convolutional neural network (CNN) is a series of multiple MAMS-blocks. It enables significant information to be expressed at more levels, and can also be easily grafted into different convolutional structures. Limited by hardware conditions, we only prove the validity of the proposed ideas through convolutional networks of the same magnitude. The experimental results show that the convolution model with an attention mechanism and multi-scale features is superior in image classification.

Sea clutter and inherent speckle noise in synthetic aperture radar (SAR) images can pose challenges to accurate sea surface target detection, especially for phenomena such as ship wakes reliant on efficient feature extraction. Traditional denoising methods require manual trade-offs between denoising effects and detail retention. Supervised denoising methods based on deep learning demand a substantial number of real noisy-clean image pairs for training, coupled with specific parameter settings and labeled data amounts. In response to these challenges, this paper introduces Wake2Wake, a self-supervised denoising method aimed at enhancing the performance of existing deep learning-based ship wake detectors. The method incorporates a novel ship wake awareness (SWA) block designated to address the distinctive features of turbulent and Kelvin wakes. Furthermore, to overcome the source imbalance problem in the dataset, simulated wake data is integrated into the training process. This not only mitigates dataset imbalances but also significantly improves both denoising and detection performance. The experimental results indicate that Wake2Wake improves the accuracy of Rotated RepPoints by 3.6 mAP and S ² A-Net by 2.6 mAP on the OpenSARWake dataset, respectively. The proposed approach achieves varied extents of improvement, showcasing its potential in mitigating sea clutter and enhancing feature extraction, especially in detecting SAR ship wakes.

The Kelvin wake, a distinctive ship-generated wave pattern in synthetic aperture radar (SAR) imagery, plays a vital role in advancing ocean observation theory. Current simulations rely on approximations that neglect critical physical mechanisms: time-varying characteristics and decoherence effects, sensitivity to the integration time, relative angle between ship heading and radar azimuth, and different sea conditions. To overcome resulting simulation-reality discrepancies, we propose KWFull-Link SARSim—a full-link model integrating ocean surface motion, time-varying scattering, and decoherence effects. Analyses demonstrate that L-band SAR suffers certain wake visibility degradation due to time-varying characteristics, especially in air-borne scenarios, while wake contrast exhibits marked dependence on ship-SAR azimuth alignment. Further, ocean cut-off wavelengths significantly influence signatures. Validation against ten real SAR images (TerraSAR-X, Sentinel-1A, ALOS PALSAR) confirms model efficacy: pronounced time-varying characteristics and decoherence effect in ALOS L-band explain wake erasure, while azimuth misalignment in Sentinel-1A C-band causes unilateral visibility loss. We establish that faithful Kelvin wake simulation must explicitly incorporate (i) platform-dependent time-varying characteristics and (ii) azimuth-modulated decoherence effects, overcoming critical limitations of traditional methods.

The inversion of ocean currents is a significant challenge and area of interest in ocean remote sensing. Spaceborne along-track interferometric synthetic aperture radar (ATI-SAR) has several advantages and benefits, including precise observations, extensive swath coverage, and high resolution. However, a limited number of spaceborne interferometric synthetic aperture radar (InSAR) systems are operating in orbit. Among these, the along-track baseline length is generally suboptimal, resulting in low inversion accuracy and difficulty in achieving operational stability. One of the approaches involves employing lower-frequency bands such as the L band to increase the baseline length to achieve the optimal baseline for a satellite formation. The LuTan-1 mission, the world’s first L-band distributed spaceborne InSAR system, was successfully launched on 27 February 2022. L-band distributed formation operation provides insight into the development of future spaceborne ATI systems with application to new exploration regimes and under optimal baseline conditions. There are two novel aspects of this investigation: (1) We described the ocean current inversion process and results based on LuTan-1 SAR data for the first time. (2) A cross-track baseline component phase removal method based on parameterized modeling was proposed for distributed InSAR systems. Both qualitative and quantitative comparisons validated the effectiveness and accuracy of the inversion results.