The rapid development of unmanned aerial vehicle (UAV) technology has contributed to the increasing sophistication of UAV-based object-detection systems, which are now extensively utilized in civilian and military sectors. However, object detection from UAV images has numerous challenges, including significant variations in the object size, changing spatial configurations, and cluttered backgrounds with multiple interfering elements. To address these challenges, we propose SOD-YOLO, an innovative model based on the YOLOv8 model, to detect small objects in UAV images. The model integrates the receptive field convolutional block attention module (RFCBAM) in the backbone network to perform downsampling, improving feature extraction efficiency and mitigating the spatial information sparsity caused by downsampling. Additionally, we developed a novel neck architecture called the balanced spatial and semantic information fusion pyramid network (BSSI-FPN) designed for multi-scale feature fusion. The BSSI-FPN effectively balances spatial and semantic information across feature maps using three primary strategies: fully utilizing large-scale features, increasing the frequency of multi-scale feature fusion, and implementing dynamic upsampling. The experimental results on the VisDrone2019 dataset demonstrate that SOD-YOLO-s improves the mAP50 indicator by 3% compared to YOLOv8s while reducing the number of parameters and computational complexity by 84.2% and 30%, respectively. Compared to YOLOv8l, SOD-YOLO-l improves the mAP50 indicator by 7.7% and reduces the number of parameters by 59.6%. Compared to other existing methods, SODA-YOLO-l achieves the highest detection accuracy, demonstrating the superiority of the proposed method.

Unmanned aerial vehicle (UAV) image object detection has extensive applications across both civilian and military domains. However, the traditional YOLOv8 detection algorithm faces significant challenges in detecting small objects in UAV imagery, primarily due to a high missed detection rate and an excessive number of parameters. To address these issues, this paper introduces an enhanced small object detection approach, called Small-Size Object Detection Algorithm Based on Improved YOLOv8 for UAV Imagery (SS-YOLOv8). Firstly, considering the difficulties and stringent real-time requirements in detecting small objects in UAV aerial images, this work streamlines the model by eliminating the large object detection head and its associated redundant network layers, significantly limiting the parameter count. Furthermore, a specialized tiny object detection head is proposed. It is custom-designed for detecting small objects. To enhance the model’s capacity for extracting fine features of small objects and mitigate information loss during feature extraction, the convolution module is replaced in the backbone with space-to-depth convolution (SPD-Conv). Moreover, in the neck section, the self created GCU module is incorporated as it effectively amalgamates deep semantic features with shallow positional ones. Finally, while maintaining consistent parameter costs, multi-scale features are meticulously reused and incorporated to achieve a more comprehensive and sophisticated feature fusion. The experimental results on the VisDrone2019 dataset showed that compared with YOLOv8, SS-YOLOv8 improved its MAP index by 6.9% on the validation set and 5.8% on the test set, while reducing the number of parameters and model size by 65.93% and 64.85%, respectively. Compared with the best performing comparison algorithm, SS-YOLOv8 has the highest detection accuracy, indicating the superiority of this method.

The Global Navigation Satellite System (GNSS) can be utilized for long-distance and high-precision time transmission. With the ongoing development of low Earth orbit (LEO) satellites and the rapidly changing geometric relationships between them, the convergence rate of ambiguity parameters in Precise Point Positioning (PPP) algorithms has increased, enabling fast and reliable time transfer. In this paper, GPS is used as an experimental case, the LEO satellite constellation is designed, and simulated LEO observation data are generated. Then, using the GPS observation data provided by IGS, a LEO-enhanced PPP model is established. The LEO-augmented PPP model is employed to facilitate faster and more reliable high-precision time transfer. The application of the LEO-augmented PPP model to time transfer is examined and discussed through experimental examples. These examples show multiple types of time transfer links, and the experimental outcomes are uniform. GPS + LEO is compared with exclusive GPS time transfer schemes. The clock offset of the time transfer link for the GPS + LEO scheme converges more swiftly, meaning that the time required for the clock offset to reach a stable level is the briefest. In this paper, standard deviation is employed to assess stability, and Allan deviation is utilized to assess frequency stability. The results show that the clock offset stability and frequency stability achieved by the GPS + LEO scheme are superior within the convergence time range. Controlled experiments with different numbers of satellites for LEO enhancement indicate that time transfer performance can be improved by increasing the number of satellites. As a result, augmenting GPS tracking data with LEO observations enhances the time transfer service compared to GPS alone.