With the rapid development of unmanned systems, autonomous driving, and other related fields, dual dynamic carrier relative positioning technology has become increasingly important for achieving high-precision real-time positioning and adapting to complex environments. To improve the accuracy and reliability of the existing relative positioning algorithm for dual dynamic carrier, this paper proposes a dual dynamic carrier relative positioning algorithm based on Double Factor graph and Ambiguity Resolution optimization (DF-AR), incorporating reference station processing, ambiguity resolution, and mobile station resolution optimization methods. To improve relative positioning accuracy, a factor graph optimization model integrating multi-frequency and multi-system Kalman filtering is used to suppress single-point positioning errors at the reference station. Using baseline constraints along with data quality weighting, an improved data and model-driven partial ambiguity resolution strategy is constructed. The ambiguity subset with higher reliability is selected to improve the success rate of ambiguity fixation and the reliability of the relative positioning solution. Based on these improvements, a sliding window is introduced in the factor graph optimization model to dynamically adjust the data amount. The positioning solution of the mobile station is reoptimized to achieve more robust relative positioning results. Static evaluation experiments, dual-vehicle and UAV/vehicle dynamic relative positioning experiments were carried out. The experimental results show that in different experimental scenarios, the baseline solution error of the DF-AR relative positioning algorithm has an error reduction of 69.72%, 94.89%, and 68.03% compared to the RTKLIB algorithm. The baseline solution accuracy has been improved from meter level to decimeter level, effectively enhancing the reliability and accuracy of relative positioning.

An improved unmannd aerial vehicle (UAV) detection algorithm, STC-YOLOv5 is proposed to address the problem of failing to quickly and accurately identify UAV targets under complex environmental conditions, such as similar colors of the background and UAVs, and overlapping of target occlusions. The backbone feature extraction network of STC-YOLOv5 employs Swin Transformer to enhance the robustness of the network against complex environments. The YOLOv5 model feature fusion network incorporates the convolution block attention module (CBAM) to decrease superfluous feature attention and increase attention on the UAV target’s key features. The loss function is optimized according to the characteristics of UAVs, and angle loss, distance loss and shape loss are introduced into the complete-IoU (CIoU) loss function, which improves the recognition accuracy of occluded UAV targets. In the case of partially occluded UAV targets, the improved STC-YOLOv5 algorithm has an average precision of 92.98% and a recall of 87.09%, which are 2.88% and 6.03% higher than the YOLOv5 algorithm, respectively. The results of experimental validation on the independently established UAV flight dataset demonstrate that the algorithm can achieve quick and precise UAV recognition in challenging scenarios.