Recently, convolution neural networks (CNNs) have been extensively utilized in synthetic aperture radar (SAR) ship detection owing to their strong feature extraction and representation capability. However, existing CNN-based SAR ship detectors often suffer from poor sensitivity to small-scale ship targets due to the limited extractable features, especially in complex inshore scenarios. Moreover, the hand-designed components like nonmaximum suppression (NMS) calculation and anchor generation imposed in CNN-based detector significantly affect their robustness. In the face of these challenges, a novel end-to-end (E2E) transformer-based detection framework for small-scale ship targets in SAR images, named detection transformer (DETR) with improved de-noising (DN) anchor box (DINO) with refined DN and box (RDB-DINO), is proposed in this article. First, we introduce a complete contrastive DN (CCD) training technique which reconstructs and exploits different kinds of noised queries to reduce the confusion between small ships and complex backgrounds. Second, a look twice toward maximum (LTTM) algorithm for iterative box refinement is designed to mine the abnormal sample information and obtain abundant features of small ships in the training process. Finally, substantial experiments conducted on two widely used open SAR ship datasets demonstrate that the proposed approach yields superior results in small ship detection performance, outperforming prevailing state-of-the-art (SOTA) benchmarks.

Existing convolution neural network (CNN)-based synthetic aperture radar (SAR) ship detectors often suffer from poor performance to small-scale ship targets due to the scarcity of extractable features and the bottleneck of local receptive field in the CNN framework. To address the challenges, we propose a novel end-to-end transformer-based detection network for small-scale ship targets in SAR images, named DINO with Refined Denoising and Box (R2DB-DINO). First, we propose a complete contrastive denoising (CCD) training technique which can reconstruct and exploit various types of noisy queries to alleviate the confusion between small ships and background. Second, a look twice towards maximum (LTTM) algorithm for iterative box refinement is devised to acquire abundant features of prediction boxes for small ships by enhancing gradient information. Experiments conducted on measured dataset demonstrate the superiority of the proposed method in small-scale ship detection compared with existing methods.

In this paper, we proposed a novel Label Augmentation network based on Self-Distillation (LASDet) for inshore ship detection in synthetic aperture radar (SAR) images. Different from canonical convolution neural network (CNN)-based approaches under the guidance of hard label, the new semisoft labels produced by self-distillation are leveraged for ship detection to boost the information of negative sample in complex scenarios. Additionally, an angle-related balance intersection-over-union (ArBIoU) loss criterion is developed to alleviate ambiguity expression of inshore ship targets by using the adaptive weight association of the aspect ratio difference and the center point deviation in regression. Experimental results on open datasets demonstrate the superiority of the proposed method compared with the existing commonly used network, especially in complex inshore scenarios.

With the soaring development of deep learning (DL) mechanisms in recent years, convolution neural network (CNN)-based methods have been extensively investigated to achieve high accuracy of ship detection in Synthetic Aperture Radar (SAR) images. However, existing CNN-based SAR ship detection methods still suffer from challenges in complex inshore scenarios due to the strong interference therein. To tackle this issue, a novel Semi-Soft Label-guided network based on Self-Distillation (SD) for SAR ship detection (S2LSDNet) is proposed in this article. First, different from the existing CNN-based detectors to extract features from the image domain only under the guidance of one-hot label, an efficient SD training strategy is devised to extract semi-soft label information to boost the inshore ship detection accuracy. Second, an angle-related and Balanced Intersection-over-Union (ArBIoU) loss is developed to enhance the inshore ship positioning performance by using the adaptive weights of center point bias and the aspect ratio difference. Experiments on the open SAR ship detection datasets demonstrate the effectiveness and superiority of the proposed method compared with the existing state-of-the-art approaches, especially in inshore scenes.

Existing ship detection approaches in optical remote sensing images often suffer from bottlenecks in inshore scenarios due to the substantial interference. In addition, the ship targets with different orientation angles and large aspect ratios increase the difficulty to accurately profile and locate them in optical remote sensing images. To address the aforementioned issues, a novel dual separation attention network (DSA-Net) based on the skew complete intersection-over-union (SkewCIoU) loss is proposed in this letter. In our DSA-Net, we construct a contextual location module (CLM) as the spatial attention in the backbone stage and a global channel module (GCM) as the channel attention in the neck stage, respectively. The two separated attention modules enhance the discrimination between ship targets and complex inshore interferences. Moreover, a SkewCIoU loss considering both the angles and aspect ratios of ship targets is introduced to obtain a well-trained neural network with more accurate detection performance of slender ships. Experiments on the dataset of high-resolution ship collection 2016 (HRSC2016) manifest the superiority of the proposed algorithm in comparison to the existing state-of-the-art methods.

In this paper, we propose a hierarchical information acquisition system composed of a marine stationary sensor layer and an autonomous underwater vehicle (AUV) motion layer. Specifically, in the sensor layer, we design an energy-efficient clustering protocol based on the improved K-Means algorithm (ECBIK), which can implement uniform classification and select the cluster head dynamically according to energy awareness. Compared with the traditional K-Means and LEACH algorithm, our method achieves lower energy consumption and higher node survival rate, which can balance the energy load effectively to extend the life of the network. Additionally, in the AUV motion layer, we define the rotation-angle of AUV and analyze its influence quantitatively for the AUV information collection. Meanwhile, a novel Ant Colony (ACO) algorithm based on Markov Reward Process (MRP) is proposed for AUV path planning. As the simulation experiments indicate, our algorithm can achieve shorter distance, smaller angle, and faster convergence speed in path optimization.

Recently, the technology of underwater wireless sensors networks (UWSNs) has received more attention on the exploitation of marine resources. However, underwater acoustic communication is still the only reliable means of ocean communication, which is entirely different from the terrestrial scene. In this paper, we propose Q-learning aided ant colony routing protocol (QLACO) to address the issues of energy-efficiency and link instability in UWSNs, which uses both the reward mechanism and artificial ants to determine a global optimal routing selection. QLACO uses the reward function to adapt to the dynamic underwater environment and enhance the packet delivery ratio (PDR). Moreover, we propose an anti-void mechanism to solve the void region dilemma. Simulation results show that QLACO outperforms Q-learning-based energy-efficient and lifetime-aware routing protocol (QELAR) and the depth-based protocol (DBR) in terms of PDR, energy consumption and latency.