Ship detection technology has achieved significant progress recently. However, for practical applications, lightweight ship detection still remains a very challenging problem since small ships have small relative scales in wide images and are easily missed in the background. To promote the research and application of small-ship detection, we propose a new remote sensing image dataset (VRS-SD v2) and provide a fog simulation method that reflects the actual background in remote sensing ship detection. The experiment results show that the proposed fog simulation is beneficial in improving the robustness of the model for extreme weather. Further, we propose a lightweight detector (LMSD-Net) for ship detection. Ablation experiments indicate the improved ELA-C3 module can efficiently extract features and improve the detection accuracy, and the proposed WGC-PANet can reduce the model parameters and computation complexity to ensure a lightweight nature. In addition, we add a Contextual Transformer (CoT) block to improve the localization accuracy and propose an improved localization loss specialized for tiny-ship prediction. Finally, the overall performance experiments demonstrate that LMSD-Net is competitive in lightweight ship detection among the SOTA models. The overall performance achieves 81.3% in AP@50 and could meet the lightweight and real-time detection requirements.

Ship detection in visible remote sensing (VRS) images has been widely used in the military and civil fields. However, the various backgrounds and the variable scale and orientation bring great difficulties to effective detection. In this paper, we propose a novel ship target detection scheme based on small training samples. The scheme contains two main stages: candidate region extraction and ship identification. In the first stage, we propose a visual saliency detection model based on the difference in covariance statistical characteristics to quickly locate potential ships. Moreover, the multi-scale fusion for the saliency model is designed to overcome the problem of scale variation. In the second stage, we propose a three-channel aggregate feature, which combines a rotation-invariant histogram of oriented gradient and the circular frequency feature. The feature can identify the ship target well by avoiding the impact of its rotation and shift. Finally, we propose the VRS ship dataset that contains more realistic scenes. The results on the VRS ship dataset demonstrate that the saliency model achieves the best AUC value with 0.9476, and the overall detection achieves a better performance of 65.37% in terms of AP@0.5:0.95, which basically meets the need of the detection tasks.

Vehicle detection on aerial remote sensing images under the complex background of urban areas has always received great attention in the field of remote sensing; however, the view of remote sensing images usually covers a large area, and the size of the vehicle is small and the background is complex. Therefore, compared with object detection in the ground view images, vehicle detection in aerial images remains a challenging problem. In this paper, we propose a single-scale rapid convolutional neural network (SSRD-Net). In the proposed framework, we design a global relational (GR) block to enhance the fusion of local and global features; moreover, we adjust the image segmentation method to unify the vehicle size in the input image, thus simplifying the model structure and improving the detection speed. We further introduce an aerial remote sensing image dataset with rotating bounding boxes (RO-ARS), which has complex backgrounds such as snow, clouds, and fog scenes. We also design a data augmentation method to get more images with clouds and fog. Finally, we evaluate the performance of the proposed model on several datasets, and the experimental results show that the recall and precision are improved compared with existing methods.

Moving object detection in remote sensing image sequences has been widely used in military and civilian fields. However, the complex background of remote sensing images and the small sizes of moving objects bring great difficulties for effective detection. To solve this problem, we propose a real-time moving object detection method for remote sensing image sequences. This method works by fusing the semantic information from a single image extracted by the object detection branch with the motion information of multiple frames extracted by the motion detection branch. Specifically, in the motion detection branch, we design a motion feature enhancement module (MFE) to improve the interframe motion information. Then, we design a Motion Information Extraction network (MIE) to extract motion information. Finally, the moving object information is directly output by fusing the motion and semantic information extracted by the object detection branch. Based on the experimental results of the two datasets, the proposed method achieves an accuracy rate of 93.21%, a recall rate of 92.72%, an average frame rate of 25.25 frames (fps), and a performance of 96.71% in terms of AP@0.5. The performance of the proposed method is better than that of other methods, and the overall detection effect is better; therefore, it meets the needs of the detection task.

Oriented object detection in remote sensing images has attracted significant attention, as rotated bounding boxes can more accurately fit targets with arbitrary orientations. However, existing oriented detection models still struggle with challenges such as angle regression instability and ambiguity caused by angle periodicity and edge exchange, which hinder their effectiveness in practical remote sensing applications. To address these issues, we propose a one-stage heatmap-based rotated object detector, named RANet. In this framework, we introduce Correlated Vector Labels (CVL) to simultaneously tackle the Periodicity of Angle (PoA) problem and the Exchange of Edges (EoE) issue. Furthermore, RANet leverages pixel-level features around extreme points to perform unbiased coordinate estimation through a Taylor expansion, improving localization accuracy. To enhance training stability and performance, we design a Swap Vector Loss (SVL) to optimize the angular regression for objects with varying aspect ratios, and a Continuous Focal Loss (CFL) to maintain heatmap smoothness. Extensive experiments on multiple datasets demonstrate that our method achieves superior recall and precision compared to state-of-the-art approaches.