FFC-YOLO: a SAR ship detection network with enhanced feature representation and dynamic cross-scale fusion

In recent years, the rapid development of Deep Learning (DL) has provided a new method for ship detection in Synthetic Aperture Radar (SAR) images. However, there are still four challenges in this task. (1) The ship targets in SAR images are very sparse. A large number of unnecessary anchor boxes may be generated on the feature map when using traditional anchor-based detection models, which could greatly increase the amount of computation and make it difficult to achieve real-time rapid detection. (2) The size of the ship targets in SAR images is relatively small. Most of the detection methods have poor performance on small ships in large scenes. (3) The terrestrial background in SAR images is very complicated. Ship targets are susceptible to interference from complex backgrounds, and there are serious false detections and missed detections. (4) The ship targets in SAR images are characterized by a large aspect ratio, arbitrary direction and dense arrangement. Traditional horizontal box detection can cause non-target areas to interfere with the extraction of ship features, and it is difficult to accurately express the length, width and axial information of ship targets. To solve these problems, we propose an effective lightweight anchor-free detector called R-Centernet+ in the paper. Its features are as follows: the Convolutional Block Attention Module (CBAM) is introduced to the backbone network to improve the focusing ability on small ships; the Foreground Enhance Module (FEM) is used to introduce foreground information to reduce the interference of the complex background; the detection head that can output the ship angle map is designed to realize the rotation detection of ship targets. To verify the validity of the proposed model in this paper, experiments are performed on two public SAR image datasets, i.e., SAR Ship Detection Dataset (SSDD) and AIR-SARShip. The results show that the proposed R-Centernet+ detector can detect both inshore and offshore ships with higher accuracy than traditional models with an average precision of 95.11% on SSDD and 84.89% on AIR-SARShip, and the detection speed is quite fast with 33 frames per second.

Ship detection in synthetic aperture radar (SAR) images has attracted extensive attention due to its promising applications. While numerous methods for ship detection have been proposed, detecting ships in complex scenarios remains challenging. The main factors contributing to the lower detection accuracy are SAR image characteristics, such as blurred outlines, and similar scattering intensities between actual ship targets and background environment, induced by the special imaging mechanism. To alleviate these issues, we propose a Mixed-scale Self-distillation Network (MSNet) for accurate ship detection in SAR images. Firstly, the zoom strategy is used to obtain more ship target information, and differentiated information between ship targets and background environments at different scales is aggregated through the designed search module. Then, the consistency self-distillation module is proposed to match feature attention maps at different scales, which forces the model to capture the potential semantic attributes of ship targets through a self-distillation fashion. After that, the refinement module is developed to further enhance the discriminative semantics among different hierarchical features under mixed scales. Furthermore, to alleviate the uncertainty arising from indistinguishable background interference in SAR images, we introduce an uncertainty perception loss to facilitate the model to make accurate judgments in candidate regions. Extensive experiments are performed on the SAR ship detection dataset from the Gaofen-3, RadarSat-2, Sentinel-1, and TerraSAR satellites. The experimental results consistently demonstrate the superiority of our method over the existing state-of-the-art methods. Besides, detailed model analysis experiments further validate the effectiveness of our proposed method in SAR image ship detection tasks. The code will be available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/shuangliumax/MSNet/</uri>

Ship detection using synthetic aperture radar (SAR) has been extensively utilized in both the military and civilian fields. On account of complex backgrounds, large scale variations, small-scale targets, and other challenges, it is difficult for current SAR ship detection methods to strike a balance between detection accuracy and computation efficiency. To overcome those challenges, ESarDet, an efficient SAR ship detection method based on contextual information and a large effective receptive field (ERF), is proposed. We introduce the anchor-free object detection method YOLOX-tiny as a baseline model and make several improvements to it. First, CAA-Net, which has a large ERF, is proposed to better merge the contextual and semantic information of ships in SAR images to improve ship detection, particularly for small-scale ships with complex backgrounds. Further, to prevent the loss of semantic information regarding ship targets in SAR images, we redesign a new spatial pyramid pooling network, namely A2SPPF. Finally, in consideration of the challenge posed by the large variation in ship scale in SAR images, we design a novel convolution block, called A2CSPlayer, to enhance the fusion of feature maps from different scales. Extensive experiments are conducted on three publicly available SAR ship datasets, DSSDD, SSDD, and HRSID, to validate the effectiveness of the proposed ESarDet. The experimental results demonstrate that ESarDet has distinct advantages over current state-of-the-art (SOTA) detectors in terms of detection accuracy, generalization capability, computational complexity, and detection speed.

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.

Density-based ship detection in SAR images: Extension to a self-similarity perspective

Generative knowledge transfer for ship detection in SAR images

Ship detection from synthetic aperture radar (SAR) images is a hot topic, but the difficulty in collecting labeled SAR images may hinder the development of deep-learning-based detection methods. Inspired by the idea of domain adaptation, in this article, we propose a hierarchical similarity alignment neural network (HSANet) for ship detection in SAR images, which is a domain adaptive (DA) approach with optical remote sensing images as training samples. The kernel target of HSANet is to mine and align both the global structure and the local instance information between SAR and optical images, where two modules, structural alignment module (SAM) and prototype alignment module (PAM), are designed to, respectively, conduct two hierarchies of alignment process. In general, SAM attempts to extract the global structure similarity which exists in image-level feature representation, while PAM tends to extract the local shape similarity which is instance-level representation. To be specific, SAM is developed by Fourier-based feature alignment, which tries to describe the similar structural relationship between optical and SAR images. Meanwhile, PAM is proposed based on the conjoint confidence analysis where the instance-level ship representations of the source and target domains is aligned. SAM and PAM work together to construct a hierarchical domain adaptation network for SAR ship detection. Experiments on several public datasets may indicate the effectiveness of the proposed 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.

Transformer-based methods have demonstrated their potential capabilities in ship detection of synthetic aperture radar (SAR) images. However, their exclusive reliance on global context information hinders the precise localization of small ships, leading to suboptimal detection performance. In this work, a global-to-local detection transformer (GL-DETR) framework is proposed to enhance the detection accuracy of small ships in SAR images. In GL-DETR, the decoder is constituted of a global layer and a carefully designed local layer. Within the global layer, object queries fully interact with global context information. Furthermore, a local interaction attention (LIA) module is designed in the local layer, with the purpose of refining and enriching the object query features through local multiscale region of interest (ROI) information. Additionally, a multiscale information enhancement (MIE) module is introduced to enhance the high-frequency information of small ships through Gaussian filtering. Numerical results demonstrate that GL-DETR outperforms baseline by 3.71% and 4.89% on classical SAR datasets LS-SSDD and HRSID, respectively. These results demonstrate the effectiveness and superiority of the proposed strategy.

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.

The sizes of ships vary by type in synthetic aperture radar (SAR) images, and this multiscale problem degrades the accuracy of ship detection. We present a multiscale ship detection method based on cascaded dense weighted networks in SAR images. Dense weighted fusion is performed in the feature extraction module and feature fusion module by cascading, i.e., feature weighting is achieved by embedding a convolutional block attention module after feature layers at different scales, followed by dense connection to fuse features at different scales. This makes it possible to refine the cascaded feature mapping, enhance the information transfer of shallow and deep features, and build a multiscale feature representation model. Experiments on the extended high-resolution SAR images dataset show that the accuracy of this method is 74.87% in inshore scenes, and 97.39% in offshore scenes, which exceeds that of other ship detection methods. In addition, in two SAR images from TerraSAR-X, the detection accuracy of multiscale ships reaches 86.63%, which indicates the method’s better robustness.

Ship detection in low-quality Synthetic Aperture Radar (SAR) images poses a persistent challenge. Noise signals in complex environments disrupt imaging conditions, hindering SAR systems from acquiring precise target information, thereby significantly compromising the performance of detectors. Some methods mitigate interference via denoising techniques, while others introduce noise using classical methods to learn target features in the presence of noise. This conundrum is regarded as a cross-domain problem in this paper; a ship detection method in low-quality images is proposed to learn features of targets and shrink serious deterioration of detection performance by utilizing Generative Adversarial Networks (GANs). First, an image-to-image translation task is implemented using CycleGAN to generate low-quality SAR images with complex interference from the source domain to the target domain. Second, with the annotation inheritance, these generated SAR images participate in a training process to improve the detection accuracy and model robustness. Multiple experiments indicate that the proposed method conspicuously improves the detection performance and efficaciously reduces the missed detection rate in the SAR ship detection task. This cross-domain approach achieved outstanding improvements in the form of 11.0% mAP and 3.22% mAP on the GaoFen-3 ship dataset and SRSSD-V1.0, respectively. In addition, the characteristics and potentials of near-shore and off-shore SAR image reconstruction with style transfer based on Generative Adversarial Networks were explored and analyzed in this work.

Fisher vectors (FVs) can capture multiple order information from superpixels (SPs) in synthetic aperture radar (SAR) images. Existing FV-based ship detectors mainly exploit the local contrast of FVs (LCFVs) but do not consider their global density features. This may lead to degraded performance in terms of discrimination between ship targets and the complex sea clutter. In this article, two new global cues from FVs are designed based on the fact that target FVs exhibit much lower densities than those of clutter FVs and also have large distances to the latter. Our two new global cues can suppress the sea clutter and significantly enhance ship targets throughout the SAR image. We also design an improved local cue from FVs for ship detection, in which the intensity contrast of SPs is incorporated into the existing LCFV indicator to reduce false alarms. By fusing the above two new global cues (and an improved local cue from FVs), we propose a new method for ship detection in SAR images. Experimental results based on Gaofen-3 SAR images show that the newly proposed detector provides better detection performance than other state-of-the-art detectors, especially in the presence of strong and highly heterogeneous sea clutter.

Ship detection in synthetic aperture radar (SAR) images is critical to ocean surveillance and rescue. Although many deep learning SAR ship detection methods have been proposed, the performance of these methods depends on the size and quality of the training samples. To resolve these issues, this letter presents an unsupervised ship detection method in SAR images using superpixel segmentation and cross stage partial network (CSPNet). First, the SAR image is over-segmented into superpixels based on our previously proposed superpixel generation algorithm. Then, the complex signal kurtosis (CSK) and a local superpixel contrast are integrated as a statistical indicator for the automatic identification of ship superpixels and background superpixels, thus leading to generation of training samples. Finally, the segmented superpixels are input to the CSPNet, which can learn a representative feature set with high discrimination ability between ships and backgrounds. Our method can achieve pixel-level detection map rather than the bounding box result. Experiments based on the Gaofen-3 and TerraSAR SAR data demonstrate that our method can achieve above 90% actual detection rate.