9 January 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
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.
6 March 2023 in IEEE Geoscience and Remote Sensing Letters
Most synthetic aperture radar (SAR) ship detectors based on convolutional neural networks (CNNs) needed preset anchor boxes to object classification and bounding box coordinate regression. However, the sparsity and unbalanced distribution of ships in SAR images mean that most anchor boxes are redundant. Thus, the anchor settings directly affect the performance and generalization ability of the detector. In addition, a variety in ship scales and the substantial interference of inshore backgrounds bring significant challenges to the SAR ship detector’s performance improvement. In this letter, a novel anchor-free-based detector, named feature balance and united attention (FBUA-Net), is proposed. We adopt a keypoint-based strategy to predict bounding boxes to eliminate the influence of anchors. Besides, we propose a global context-guided feature balanced pyramid (GC-FBP), which balances the semantic information at different levels of the feature pyramid by aggregation and averaging and uses the global context module (GCM) to learn global contextual information to construct long-range dependencies between ship targets and the background. Considering the interference of scattering noise to the detector, a united attention module (UAM) is designed to reduce the interference of surrounding noise by focusing on the spatial shape and scale size of ship targets in both the spatial and scale domains. Experimental results on the SAR ship detection dataset (SSDD) and high-resolution SAR images dataset (HRSID) datasets show that our detector achieves state-of-the-art (SOTA) performance. The source code can be found at https://github.com/so-bright/FBUA-Net .
23 June 2022 in IEEE Geoscience and Remote Sensing Letters
With the development of deep learning, remote sensing image (RSI) semantic segmentation has produced significant advances. The majority of existing methods use fully convolutional network (FCN) that lacks fine-grained multiscale representation and fails to extract global context information. Thus, we improve FCN by adding two modules—multiscale attention (MSA) and nonlocal filter (NLF). The MSA module enhances the network’s fine-grained multiscale representation capability and allows modeling the interdependencies of feature maps among different channels. The NLF module can capture global context information by sequential using fast Fourier transform (FFT), parameter learnable filters, and inverse FFT. By using MSA module for encoder and NLF module for decoder in the FCN framework, MSA and NLF network (MsanlfNet) can obtain both fine-grained multiscale spatial feature and global context information, thus achieving a balance between performance and computational effort. Experimental results on the remote sensing semantic segmentation public datasets demonstrate that our method can achieve better performance. The code is available at https://github.com/xyuanLin/MsanlfNet .