当前，一些单目标跟踪算法已经取得了领先的性能，但庞大的模型限制了其在无人机这样资源有限平台上的应用。为此，设计了一种基于孪生网络的轻量型无人机单目标跟踪算法，旨在消耗更少资源情况下实现对目标的高效跟踪。首先，基于MobileNetV3设计了轻量化的孪生特征提取骨干网络，在保证不降低特征提取能力的前提下，极大减少网络的计算量和参数量。其次，设计了双重互相关模块，该模块采用像素互相关快速实现模板图像特征和搜索图像特征的相似性计算，同时结合深度互相关补充缺失特征，有效提升特征匹配的精度和鲁棒性。然后，通过堆叠多个深度可分离卷积层设计了轻量化的预测头部，以最小化的资源消耗来获得准确的目标表达。最后，在传统的分类和回归损失基础上，引入分类排名损失，增强网络对目标前景的学习能力，抑制背景干扰，进一步提升跟踪性能。综合实验表明：算法以5.3×10⁵的参数量和1.1×10⁸的浮点数运算量，在无人机视频目标跟踪数据集DTB70、UAV123和UAV20L上分别取得82.1%、81.2%和64.6%的准确率以及63.4、61.8%和49.6%的成功率，达到同类跟踪算法的性能且参数量和计算量大幅降低，并能以100 fps以上的速度运行，满足无人机目标跟踪的实时性需求。

Currently， some single object tracking algorithms have achieved leading performance， but their large models limit their application on resource-constrained platforms such as Unmanned Aerial Vehicles （UAVs）. This paper designs a lightweight single object tracking algorithm for UAVs based on the Siamese network to achieve efficient tracking with less resource consumption. Firstly， a lightweight backbone network for Siamese feature extraction is designed based on MobileNetV3， significantly reducing the computation and parameter volume of the network without compromising feature extraction capabilities. Secondly， a dual cross-correlation module is designed. The module uses Pointwise Cross-Correlation to quickly calculate the similarity between template image features and search image features and also uses Depthwise Cross-Correlation to supplement missing features， effectively enhancing feature matching accuracy and robustness. Then， a lightweight prediction head is designed by stacking multiple depthwise separable convolution layers， obtaining accurate target representations with minimal performance consumption. Finally， classification ranking loss is introduced to traditional classification and regression losses， enhancing the network’s ability to learn target foreground and suppress background interference， and further improving tracking performance. Comprehensive experiments show that the proposed algorithm achieves 82.1%， 81.2%， and 64.6% precision and 63.4%， 61.8%， and 49.6% success rate on DTB70， UAV123， and UAV20L datasets， respectively， with only 5.3×10⁵ parameters and 1.1×10⁸ floating point operations. It achieves the performance comparable to state-of-the-art tracking algorithms， while having significantly fewer parameters and computational load， and it can run at the speeds above 100 fps， meeting the real-time requirements of UAV object tracking.