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.

A key issue of existing deep-learning-based object detection methods in remote sensing images is that they often struggle to differentiate the background and small object regions due to multi-level downsampling operations therein. Downsampling operations help extract high-level semantic features but result in excessive loss of spatial features of small objects. In this paper, we propose a new small object detector using multispectral remote sensing images, named content-aware downsampling-based detection network (CADDN), where we newly design a content-aware downsampling-based module (CADM). Unlike conventional downsampling operations that apply uniform downsampling parameters across the entire feature map, CADM adaptively assigns higher weights to feature elements that are critical for distinguishing objects from the background, and this assignment is guided by the contextual awareness of object locations during the downsampling process. Experiments based on multispectral remote sensing images with small ships and vehicles demonstrate that CADM can accurately identify and preserve the locations of important object-related features, and CADDN correspondingly achieves superior small object detection performance than state-of-the-art methods.

The fusion module of RGB and infrared (IR) remote sensing images is the key of multispectral ship detection. Existing works have shown that the cross-attention-based feature fusion can achieve good performance by extracting the complementary information of RGB and IR modalities. However, the existing commonly used cross-attention mechanisms introduce lots of redundancy parameters and mainly focus on global feature interaction of multispectral images, ignoring local detail information that is also important for small ship detection. In this paper, we propose a novel multispectral ship detection approach named LoGFusion. In LoGFusion, we design the cross stage partial module with partial convolution (CSPMPC) to reduce feature redundancy and utilize the local cross-modal fusion module (LoCFM) and global cross-modal fusion module (GCFM) to capture both local and global cross-modal features. Furthermore, we introduce a Multispectral Small Ship Dataset (MSSD) containing over 5k ship targets for small target detection. Experiments on MSSD validate the effectiveness of our method in terms of small ship detection in multispectral images.

Existing satellite remote sensing change detection (CD) methods often crop large-scale bi-temporal image pairs into small patch pairs and use pixel-level CD methods to fairly process all the patch pairs. However, due to the sparsity of changed areas, existing pixel-level CD methods suffer from a waste of computational cost and memory resources on many unchanged areas, which hinders the deployment of the CD model on on-board platforms with extremely limited resources. To address this issue, we propose a lightweight patch-level CD network (LPCDNet) to rapidly remove the unchanged patch pairs in large-scale bi-temporal optical image pairs, which is helpful to accelerate the subsequent pixel-level processing and reduce its memory costs. In LPCDNet, based on the multi-scale max-pooling structure, the multilayer feature compression (MLFC) module is designed to compress and fuse the multi-level feature information from backbone network. Moreover, a sensitivity-guided network pruning method is proposed to remove unimportant channels and construct a lightweight backbone network based on ResNet18. Experiments on two datasets demonstrate the effectiveness and efficiency of our proposed method compared with existing methods.

Existing deep neural network (DNN)-based target detectors in remote sensing images (RSIs) often face challenges in distinguishing small targets from the background. This is mainly because the downsampling process in DNN-based target detectors results in excessive loss of small-target-related features. This paper proposes a new small target detector in RSIs named content-perception downsampling-based target detector (CPDTD), where a novel content-perception downsampling module (CPDM) is designed to replace standard downsampling methods (e.g. pooling and convolution with stride greater than 1). CPDM encodes the input feature map and predicts the location of important features that distinguish targets from backgrounds, assigning larger weights to critical features according to the perception of the position of targets in the content during the downsampling process. Experiments on measured multispectral RSIs regarding small ship and vehicle targets demonstrate the superiorities of our proposed CPDTD in comparison with existing methods.

Convolutional neural networks (CNNs) have been widely applied in the context of ship detection in synthetic aperture radar (SAR) images, but the detection performance is still not ideal in scenarios with clutter interference. Mining frequency-domain information to suppress the sea clutter in SAR ship detection has attracted wide attention. However, existing frequency-domain ship detection methods do not process frequency-domain information adaptively, which results in the degradation of ship detection performance. To overcome this problem, this article proposes a novel deep learning network called YOLO-FA. YOLO-FA contains the proposed frequency attention module (FAM), which can process frequency-domain information of SAR images adaptively. The proposed method can suppress the sea clutter in the SAR images with the help of frequency-domain information. We evaluate the proposed method YOLO-FA on two datasets, i.e., the high-resolution SAR images’ dataset (HRSID) and SAR ship detection dataset (SSDD). Compared with the baseline method YOLOv5 and the existing commonly used methods, YOLO-FA achieves state-of-the-art detection performance on both the datasets.