Object tracking is a basic task of the uncrewed aerial vehicle (UAV)-based intelligent visual perception system. The presence of similar targets and complex backgrounds in the airborne perspective poses significant challenges to aerial trackers. However, existing target-aware or distractor-aware trackers fail to capture discriminative cues from both target and background information in a balanced manner, resulting in limited improvement. To address these issues, this paper proposes a global agent-based Target-Distractor Aware Tracker (TDAT) to enhance the discrimination of the target. TDAT comprises two effective modules: a global agent generator and an interactor. First, the generator aggregates the target and background regions into representative agents and then performs self-attention on these agents to explicitly model the global relationships between the target and backgrounds. Next, the interactor realizes the bidirectional information interaction between global agents and local regions via self-attention. Based on the global dependencies encoded in global agents, the interactor extracts target-oriented features and enhances the understanding of the target. TDAT embedded with target-distractor awareness effectively widens the gap between target and background distractors. Experimental results on multiple UAV benchmarks show that TDAT achieves outstanding performance with a speed of 34.5 frames/s. The code is available at https://github.com/xyl-507/TDAT

Synthetic aperture radar (SAR) is a technique widely used in the field of ship detection. However, due to the high ship density, fore-ground-background imbalance, and varying target sizes, achieving lightweight and high-precision multiscale ship object detection remains a significant challenge. In response to these challenges, this research presents YOLO-MSD, a multiscale SAR ship detection method. Firstly, we propose a Deep Poly Kernel Backbone Network (DPK-Net) that utilizes the Optimized Convolution (OC) Module to reduce data redundancy and the Poly Kernel (PK) Module to improve the feature extraction capability and scale adaptability. Secondly, we design a BiLevel Spatial Attention Module (BSAM), which consists of the BiLevel Routing Attention (BRA) and the Spatial Attention Module. The BRA is first utilized to capture global information. Then, the Spatial Attention Module is used to improve the network’s ability to localize the target and capture high-quality detailed information. Finally, we adopt a Powerful-IoU (P-IoU) loss function, which can adjust to the ship size adaptively, effectively guiding the anchor box to achieve faster and more accurate detection. Using HRSID and SSDD as experimental datasets, mAP of 90.2% and 98.8% are achieved, respectively, outperforming the baseline by 5.9% and 6.2% with a model size of 12.3 M. Furthermore, the network exhibits excellent performance across various ship scales.

Synthetic Aperture Radar (SAR) has become a highly regarded technique in the field of remote sensing due to its all-weather and all-time imaging capabilities. To address the limited generalization of SAR ship detection models caused by scarce public remote sensing data and restricted scenarios, this paper proposes an improved high-quality image generation framework Ship-SAR based on Denoising Diffusion Probabilistic Models (DDPM). Firstly, the denoising network UNet extracts the long-tail contours and multi-scale texture features of ships step by step by combining a reparameterization multi-branch structure with an efficient layer aggregation network. Secondly, this paper proposes a lightweight adaptive downsampling module that mitigates information loss in traditional downsampling processes by retaining task-relevant semantic information through a dynamic feature selection mechanism. Additionally, a depth spatial upsampling block is introduced to rearrange channel dimension information into the spatial dimension, which achieves resolution enhancement. Thirdly, Ship-SAR introduces an epsilon scaling strategy to mitigate input data bias between training and sampling stages. This approach corrects sampled trajectories without requiring retraining, significantly enhancing generation quality. Ship-SAR generates SAR ship images that compare favorably to baseline DDPM in terms of Fréchet inception distance metrics and structural similarity index measure. YOLOv11s achieved an increase in mAP from 87.4% to 90.9% on high-resolution SAR image datasets and an increase in mAP of 2.1% for RTDETR-r50. The comparative results show that the SAR ship images generated by Ship SAR significantly improve the diversity of the Ship-SAR image dataset and promote progress in the field of remote sensing detection.