Synthetic aperture radar (SAR) is an active earth observation system with a certain surface penetration capability and can be employed to observations all-day and all-weather. Ship detection using SAR is of great significance to maritime safety and port management. With the wide application of in-depth learning in ordinary images and good results, an increasing number of detection algorithms began entering the field of remote sensing images. SAR image has the characteristics of small targets, high noise, and sparse targets. Two-stage detection methods, such as faster regions with convolution neural network (Faster RCNN), have good results when applied to ship target detection based on the SAR graph, but their efficiency is low and their structure requires many computing resources, so they are not suitable for real-time detection. One-stage target detection methods, such as single shot multibox detector (SSD), make up for the shortage of the two-stage algorithm in speed but lack effective use of information from different layers, so it is not as good as the two-stage algorithm in small target detection. We propose the two-way convolution network (TWC-Net) based on a two-way convolution structure and use multiscale feature mapping to process SAR images. The two-way convolution module can effectively extract the feature from SAR images, and the multiscale mapping module can effectively process shallow and deep feature information. TWC-Net can avoid the loss of small target information during the feature extraction, while guaranteeing good perception of a large target by the deep feature map. We tested the performance of our proposed method using a common SAR ship dataset SSDD. The experimental results show that our proposed method has a higher recall rate and precision, and the F-Measure is 93.32%. It has smaller parameters and memory consumption than other methods and is superior to other methods.

Synthetic Aperture Radar is an active remote sensing system that possesses characteristics such as all-weather capability and strong penetrability. In ship detection, SAR is widely used in military and civilian applications due to its excellent properties. However, in practical applications, SAR often faces challenges in achieving ideal imaging results due to factors such as height and sea conditions. Although deep learning-based object detection methods have achieved promising results in SAR ship detection, the small size of ship targets and complex sea clutter make it difficult to further improve the precision and recall rates of such algorithms. To address the challenge of balancing global and local features using convolution-based algorithms, this paper proposes a detection algorithm that integrates convolution and transformers. Firstly, an improved transformer module is designed, which fuses the output feature maps of the traditional convolution module and the improved transformer module through a parallel structure. Then, a novel backbone structure is developed by stacking the aforementioned parallel structures, enabling the integration of global and local features as well as the detection of multi-scale features. Experimental results demonstrate that compared to other models, the proposed method achieves more effective SAR detection in SAR images.

As the application of deep learning in general optical images becomes more and more widespread, the field of remote sensing images also begins to pay attention to the application of deep learning methods. Although deep learning detection algorithms have achieved better results than traditional detection algorithms, the detection results for poorly imaged SAR images still need improvement, and processing poorly imaged noisy SAR images is still a big challenge for existing algorithms. To address the problem of low precision and recall of existing algorithms for noisy SAR image detection, we propose a convolutional neural network detection algorithm based on min-pooling. First, we design a feature processing layer with min-pooling as the main structure to suppress the noise and then use a feature fusion layer to compensate for the missing information caused by pooling. To avoid problems such as redundancy in computation caused by the anchor-base algorithm, we choose the anchor-free algorithm as the main structure of ship detection. Finally, the model is evaluated using ordinary SAR image datasets and noisy SAR image datasets. Experiment results show that our proposed method has a better detection effect for noisy SAR images than other object detection models.

Synthetic Aperture Radar (SAR) is an active earth observation system that enables all-weather and all-daytime observation of the earth’s surface. With the increasing application of SAR in marine detection, numerous methods have been applied to ship detection in SAR images. Convolutional Neural Networks (CNNs) have achieved superior performance in ordinary optical images, prompting more researchers to adopt them in the SAR domain. However, SAR images exhibit distinct characteristics from optical images, and direct application of CNNs cannot yield optimal detection results. To better apply deep learning algorithms to SAR images, this paper proposes a Transformer multi-scale mapping object detection algorithm, which uses Transformer sampling modules at different scales to model SAR images. Experiments demonstrate that the proposed method can more effectively handle SAR ship images compared with other algorithms.