无人机已被广泛应用在军事和民用领域，目标跟踪是无人机应用的关键技术之一。针对无人机目标跟踪中，目标易发生形变、遮挡、尺度变化以及复杂环境等问题，提出一种基于自适应模板更新的Transformer无人机目标跟踪算法。首先，基于改进非对称注意力机制构建Transformer骨干网络，有效提取图像特征并增强特征对目标的表达能力。其次，提出一种基于外观变化系数的自适应模板更新策略。通过计算外观变化系数，自适应进行模板更新，提升跟踪网络处理目标变化的能力。最后，根据搜索区域图像特征响应图计算最大置信分数，确定目标位置。仿真实验结果表明，该算法能够有效提升无人机目标跟踪的精度，具有较好的鲁棒性。

Unmanned aerial vehicles (UAVs) have been extensively deployed in both military and civilian applications, where target tracking plays a critical role. However, UAV target tracking faces numerous challenges, including target defor-mation, occlusion, scale variation, and complex environmental conditions. To address these issues, this paper pro-poses a Transformer-based UAV target tracking algorithm with adaptive template updating. Specifically, a Transform-er backbone network is constructed using an improved asymmetric attention mechanism to effectively extract image features and enhance the representation of target-related information. Furthermore, an adaptive template updating strategy based on an appearance variation coefficient is introduced. By dynamically computing this coefficient, the template is updated adaptively to improve the network’s ability to cope with appearance changes of the target. Finally, the target position is determined by calculating the maximum confidence score from the response map of the search region. Experimental results demonstrate that the proposed algorithm significantly improves the accuracy of UAV tar-get tracking and exhibits strong robustness under challenging scenarios.