Data Matters: Rethinking the Data Distribution in Semi-Supervised Oriented SAR Ship Detection

In recent years, the growing demand for synthetic aperture radar (SAR) ship detection on mobile and satellite platforms has made lightweight detection models an important research focus. However, existing SAR ship detection methods are often limited by high computational cost and inefficient utilization of intrinsic SAR characteristics, particularly the loss of edge and high-frequency information during downsampling and the insufficient interaction of multi-scale features across network layers. To address these issues, we propose a lightweight and efficient detection framework named ESENet, which is designed from the perspective of preserving discriminative information, improving cross-scale feature interaction, and reducing structural redundancy. Specifically, a lightweight feature extraction module is introduced to alleviate high-frequency and edge information loss caused by conventional pooling operations, thereby enhancing the representation of small and low-contrast ship targets commonly present in SAR images. Furthermore, a Slender bidirectional feature pyramid network is designed by streamlining cross-layer connections and reducing redundant fusion paths, enabling effective multi-scale feature aggregation with lower computational complexity while strengthening edge-aware feature propagation. In addition, an optimized detection head with parameter sharing across scales is employed to further reduce model parameters and computational overhead without sacrificing detection accuracy or inference speed. Extensive experiments conducted on multiple public SAR ship detection datasets demonstrate the effectiveness of the proposed ESENet, achieving average accuracy rates of 91.1% on HRSID, 98.9% on SSDD, 97.3% on SSDD+, and 72.1% on synthetic and real-world small-object ship detection dataset, while maintaining a compact model size of only 1.3 M parameters, which confirms its suitability for resource-constrained SAR ship detection applications.

Ship detection in synthetic aperture radar (SAR) images is becoming a research hotspot. In recent years, as the rise of artificial intelligence, deep learning has almost dominated SAR ship detection community for its higher accuracy, faster speed, less human intervention, etc. However, today, there is still a lack of a reliable deep learning SAR ship detection dataset that can meet the practical migration application of ship detection in large-scene space-borne SAR images. Thus, to solve this problem, this paper releases a Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0) from Sentinel-1, for small ship detection under large-scale backgrounds. LS-SSDD-v1.0 contains 15 large-scale SAR images whose ground truths are correctly labeled by SAR experts by drawing support from the Automatic Identification System (AIS) and Google Earth. To facilitate network training, the large-scale images are directly cut into 9000 sub-images without bells and whistles, providing convenience for subsequent detection result presentation in large-scale SAR images. Notably, LS-SSDD-v1.0 has five advantages: (1) large-scale backgrounds, (2) small ship detection, (3) abundant pure backgrounds, (4) fully automatic detection flow, and (5) numerous and standardized research baselines. Last but not least, combined with the advantage of abundant pure backgrounds, we also propose a Pure Background Hybrid Training mechanism (PBHT-mechanism) to suppress false alarms of land in large-scale SAR images. Experimental results of ablation study can verify the effectiveness of the PBHT-mechanism. LS-SSDD-v1.0 can inspire related scholars to make extensive research into SAR ship detection methods with engineering application value, which is conducive to the progress of SAR intelligent interpretation technology.

Synthetic Aperture Radar (SAR) Ship Detection (SSD) is an important application, and it has been widely used in commercial and military fields. With the development of remote sensing technology, the use of a large amount of increasing unlabeled data is a challenge for model training, and the interference caused by the reefs and the nearshore facilities is also a challenge for SAR ship detection. In this work, we propose a Feature Integration Attention Detection (FIAD) Network to detect ships in SAR images, namely the FIAD Net. The FIAD Net has two contributions: a ModiBYOL method based on self-supervised learning and a novel Feature Integration Attention (FIA) module. The FIA module could enhance the feature learning ability of the backbone network, and the ModiBYOL could utilize the unlabeled data as a source for backbone pre-training. Experiments on the OpenSARShip dataset, the SAR ship detection dataset (SSDD), and the SAR Ship dataset show that the proposed method achieves an accuracy comparable to the state-of-art methods with a speed of 47 Frames Per Second (FPS). Besides, the effectiveness of the proposed modules is studied through an ablation study.

Synthetic aperture radar (SAR) ship detection based on deep learning has been widely applied in recent years. However, two main obstacles are hindering SAR ship detection. First, the identification of ships in a port is seriously disrupted by the presence of onshore buildings. It is difficult for the existing detection algorithms to effectively distinguish the targets from such a complex background. Additionally, it appears more complicated to accurately locate densely arranged ships. Second, the ships in SAR images exist at a variety of scales due to multiresolution imaging modes and the variety of ship shapes; these pose a much greater challenge to ship detection. To solve the above problems, this paper proposes an object detection network combined with an attention mechanism to accurately locate targets in complex scenarios. To address the diverse scales of ship targets, we construct a loss function that incorporates the generalized intersection over union (GIoU) loss to reduce the scale sensitivity of the network. For the final processing of the results, soft nonmaximum suppression (Soft-NMS) is also introduced into the model to reduce the number of missed detections for ship targets in the presence of severe overlap. The experimental results reveal that the proposed model exhibits excellent performance on the extended SAR ship detection dataset (SSDD) while achieving real-time detection.

Synthetic Aperture Radar (SAR) ship detection has been a research hotspot and is significant for marine surveillance. Traditional constant false alarm rate (CFAR) detector has the disadvantages of high false alarm and poor adaptability. Deep learning provides a unique solution for SAR ship detection. However, the traditional deep network cannot reach very deep thus the accuracy is limited, and the training speed is slow. In this paper, a very deep network ResNet with higher accuracy and faster training speed is applied to train the SAR ship detection model. Moreover, transfer learning is applied to combat the small dataset. The proposed method is tested on a general SAR ship dataset and achieves 94.7% average precision. Comparative experiments show that our method has the best performance and which verifies the effectiveness of our method.

Due to its great application value in the military and civilian fields, ship detection in synthetic aperture radar (SAR) images has always attracted much attention. However, ship targets in High-Resolution (HR) SAR images show the significant characteristics of multi-scale, arbitrary directions and dense arrangement, posing enormous challenges to detect ships quickly and accurately. To address these issues above, a novel YOLO-based arbitrary-oriented SAR ship detector using bi-directional feature fusion and angular classification (BiFA-YOLO) is proposed in this article. First of all, a novel bi-directional feature fusion module (Bi-DFFM) tailored to SAR ship detection is applied to the YOLO framework. This module can efficiently aggregate multi-scale features through bi-directional (top-down and bottom-up) information interaction, which is helpful for detecting multi-scale ships. Secondly, to effectively detect arbitrary-oriented and densely arranged ships in HR SAR images, we add an angular classification structure to the head network. This structure is conducive to accurately obtaining ships’ angle information without the problem of boundary discontinuity and complicated parameter regression. Meanwhile, in BiFA-YOLO, a random rotation mosaic data augmentation method is employed to suppress the impact of angle imbalance. Compared with other conventional data augmentation methods, the proposed method can better improve detection performance of arbitrary-oriented ships. Finally, we conduct extensive experiments on the SAR ship detection dataset (SSDD) and large-scene HR SAR images from GF-3 satellite to verify our method. The proposed method can reach the detection performance with precision = 94.85%, recall = 93.97%, average precision = 93.90%, and F1-score = 0.9441 on SSDD. The detection speed of our method is approximately 13.3 ms per 512 × 512 image. In addition, comparison experiments with other deep learning-based methods and verification experiments on large-scene HR SAR images demonstrate that our method shows strong robustness and adaptability.

In light of recent advances in deep learning and Synthetic Aperture Radar (SAR) technology, there has been a growing adoption of ship detection models that are based on deep learning methodologies. However, the efficiency of SAR ship detection models is significantly impacted by complex backgrounds, noise, and multi-scale ships (the number of pixels occupied by ships in SAR images varies significantly). To address the aforementioned issues, this research proposes a Pyramid Pooling Attention Network (PPA-Net) for SAR multi-scale ship detection. Firstly, a Pyramid Pooled Attention Module (PPAM) is designed to alleviate the influence of background noise on ship detection while its parallel component favors the processing of multiple ship sizes. Different from the previous attention module, the PPAM module can better suppress the background noise in SAR images because it considers the saliency of ships in SAR images. Secondly, an Adaptive Feature Balancing Module (AFBM) is developed, which can automatically balance the conflict between ship semantic information and location information. Finally, the detection capabilities of the ship detection model for multi-scale ships are further improved by introducing the Atrous Spatial Pyramid Pooling (ASPP) module. This innovative module enhances the detection model’s ability to detect ships of varying scales by extracting features from multiple scales using atrous convolutions and spatial pyramid pooling. PPA-Net achieved detection accuracies of 95.19% and 89.27% on the High-Resolution SAR Images Dataset (HRSID) and the SAR Ship Detection Dataset (SSDD), respectively. The experimental results demonstrate that PPA-Net outperforms other ship detection models.

Recently, convolutional neural network based methods have been studied for ship detection in optical remote sensing images. However, it is challenging to apply them to microwave synthetic aperture radar (SAR) images. First, most of the regions in the inshore scene include scattered spots and noises, which dramatically interfere with ship detection. Besides, SAR ship images contain ship targets of different sizes, especially small ships with dense distribution. Unfortunately, small ships have fewer distinguishing features making it difficult to be detected. In this article, we propose a novel SAR ship detection network called feature enhanced pyramid and shallow feature reconstruction network (FEPS-Net) to solve the above problems. We design a feature enhancement pyramid, which includes a spatial enhancement module to enhance spatial position information and suppress background noise, and the feature alignment module to solve the problem of feature misalignment during feature fusion. Additionally, to solve the problem of small ship detection in SAR ship images, we design a shallow feature reconstruction module to extract semantic information from small ships. The effectiveness of the proposed network for SAR ship detection is demonstrated by experiments on two publicly available datasets: SAR ship detection dataset and high-resolution SAR images dataset. The experimental results show that the proposed FEPS-Net has advantages in SAR ship detection over the current state-of-the-art methods.

Ship detection in Synthetic Aperture Radar (SAR) images is an important remote sensing technology. It plays an essential role in maritime monitoring and warfare. Traditional SAR ship detection methods suffer from the interference of complex backgrounds. The speckle noise and the special imaging system of SAR will deteriorate the performance of traditional methods in SAR image interpretation. Deep learning has recently been widely used in SAR image interpretation while achieving state-of-the-art performance. In this paper, a novel SAR ship detection method based on Improved You Only Look Once version 7-tiny (Improved YOLOv7-tiny) is proposed. Based on the YOLOv7-tiny network, we have made the following improvements. First, the coordinate attention is plugged into the backbone network to ensure the lightweight design. Second, the Spatial Pyramid Pooing (SPP) of the backbone network and the SIoU loss function are modified to improve performance. Eventually, the proposed method has achieved better detection performance than YOLOv7-tiny and YOLOv7 on the HRSID dataset.

A growing number of researchers begin to use the arbitrary-oriented detector to detect ships. Because in the remote sensing dataset, ships are shown to be narrow and dense. Most of the deep learning methods used in synthetic aperture radar (SAR) ship detection are the same as or variants of those of optical remote sensing. However, due to the relatively low resolution and signal-to-noise ratio, the amplitude information in SAR image becomes more contaminated than that in optical image. Therefore, it is very difficult to train the arbitrary-oriented target detection task based on SAR dataset. In order to solve this problem, we attempt to further extract the frequency domain features of the SAR image by introducing a frequency attention module. The discrete cosine transform (DCT) to converts SAR image from spatial domain to frequency domain. Experimental results on HRSID datasets show that the proposed method can significantly improve the performance of arbitrary-oriented SAR ship detection.

DL-based Synthetic Aperture Radar (SAR) ship detection has tremendous advantages in numerous areas. However, it still faces some problems, such as the lack of prior knowledge, which seriously affects detection accuracy. In order to solve this problem, we propose a scene-aware SAR ship detection method based on unsupervised sea-land segmentation. This method follows a classical two-stage framework and is enhanced by two models: the unsupervised land and sea segmentation module (ULSM) and the land attention suppression module (LASM). ULSM and LASM can adaptively guide the network to reduce attention on land according to the type of scenes (i.e., inshore scene and offshore scene) and add prior knowledge (sea-land segmentation information) to the network, thereby reducing the network's attention to land directly and enhancing offshore detection performance relatively. This increases the accuracy of ship detection and enhances the interpretability of the model. Specifically, in consideration of the lack of land–sea segmentation labels in existing deep learning-based SAR ship detection datasets, ULSM uses an unsupervised approach to classify the input data scene into inshore and offshore types and performs sea-land segmentation for inshore scenes. LASM uses the sea-land segmentation information as prior knowledge to reduce the network's attention to land. We conducted our experiments using the publicly available SSDD dataset, which demonstrated the effectiveness of our network.

Ship targets are important carriers of maritime behavior, and ship target detection has important economic and military value. Owing to its excellent characteristics, synthetic aperture radar (SAR) is widely used to detect sea targets. SAR ship detection has always been a popular field of research. The excellent performance of deep neural networks in computer vision has facilitated their application to SAR image detection. However, several problems remain in SAR ship detection at this stage. First, SAR ship targets differ significantly in size, and how to deal with multi-scale ship detection has, therefore, been a difficult research topic. Second, the size of a SAR ship target is small in low-resolution images, and thus, dealing with small size target detection is also difficult. Therefore, we propose a dense connection DetNet (DDNet), which is specifically used for SAR ship detection. The network consists of two parts: backbone sub-network and prediction sub-network. In the backbone subnetwork, we refer to DetNet, and use a stacked convolution layer instead of large downsampling to make it more suitable for small ship detection. In the prediction sub-network, we use a dense connection to fuse features of different scales, allowing it to better deal with multi-scale ship detection. The feature reuse strategy is used to improve the parameter efficiency. The experiments on SAR ship datasets show that our method performs better than other methods in small-size and complex background ship detection.

Inshore ship detection in synthetic aperture radar (SAR) imagery poses significant challenges due to the high density and diversity of ships. However, low inter-object backscatter contrast and blurred boundaries of docked ships often result in performance degradation for traditional object detection methods, especially under complex backgrounds and low signal-to-noise ratio (SNR) conditions. To address these issues, this paper proposes a novel detection framework, the Dynamic Weighted Joint Time–Frequency Feature Fusion DEtection TRansformer (DETR) Model (DWTF-DETR), specifically designed for SAR-based ship detection in inshore areas. The proposed model integrates a Dual-Domain Feature Fusion Module (DDFM) to extract and fuse features from both SAR images and their frequency-domain representations, enhancing sensitivity to both high- and low-frequency target features. Subsequently, a Dual-Path Attention Fusion Module (DPAFM) is introduced to dynamically weight and fuse shallow detail features with deep semantic representations. By leveraging an attention mechanism, the module adaptively adjusts the importance of different feature paths, thereby enhancing the model’s ability to perceive targets with ambiguous structural characteristics. Experiments conducted on a self-constructed inshore SAR ship detection dataset and the public HRSID dataset demonstrate that DWTF-DETR achieves superior performance compared to the baseline RT-DETR. Specifically, the proposed method improves mAP@50 by 1.60% and 0.72%, and F1-score by 0.58% and 1.40%, respectively. Moreover, comparative experiments show that the proposed approach outperforms several state-of-the-art SAR ship detection methods. The results confirm that DWTF-DETR is capable of achieving accurate and robust detection in diverse and complex maritime environments.

Synthetic Aperture Radar (SAR) ship object detection has important applications in maritime monitoring. Currently, CNN-based detectors are hardly perfect for multi-scale SAR ship detection by scattered noise and complex land and sea background interference. Therefore, we propose a new end-to-end method with Transformer for SAR ship detection (named TSDet). TSDet adopts an anchor-free design that can directly predict object bounding boxes and classes of multi-scale ships. Specifically, we propose Perceptual Enhancement Transformer (PET) at first, as the network structure of TSDet, which consists of the Feature Perception Enhancement (FPE) module based on self-attention and the Task Perception Enhancement (TPE) module based on cross-attention. PET can effectively suppress background noise in SAR images and enhance the salient features of ships. Second, to solve the sparse features of SAR ships, we propose a new effective sparse attention alternative to the original attention module in PET networks. It can quickly focus on important information in global features and accelerate network convergence. Finally, on the SAR-Ship dataset, our TSDet achieves the best 93.77 % AP <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</inf> , outperforming competitive benchmarks.

In recent years, convolutional neural network (CNN) has been studied extensively in synthetic aperture radar (SAR) ship detection for its powerful feature extraction and classification capability, and has significantly improved the accuracy and robustness in condition of large scenes, multi-resolutions, and complex backgrounds. At present, a lot of related research focuses on design more efficient net structures. There have not been studies on how the detection performance varies for images with different complexity, backgrounds, surroundings, and quality. Taking two open-access SAR datasets, i.e. SSDD and UCAS_SARShip, as our source datasets, this paper first divides all the images into four classes according to their surroundings and backgrounds, then, dividing each class of images to training subset, validating subset, and test subset based on their features (image quality, noise level, complexity, etc.). Secondly, a large number of SAR ship detection experiments are conducted with five representative CNN based detectors on the four datasets we made. The experimental results show that detection preference is serious for each of the five detectors when they were trained with one of the four datasets. The research in this paper is a benefit for peers to understand and analyze detection preference, besides provide some valuable reference for the collection and division of SAR datasets for ship detection in the following research.