目标跟踪在计算机视觉任务中有重要的意义。近年来随着深度学习的发展，基于孪生网络的目标跟踪算法因其优异的性能而被广泛应用。然而，现有基于孪生网络的跟踪算法在目标发生较大形变、低分辨率、复杂背景等情况下的跟踪性能通常会显著下降。为此，文中提出了一种基于多分支注意力孪生网络的目标跟踪算法。该算法首先构建了超分辨率模块和数据增强模块，分别对目标模板进行超分辨率和数据增强，提升目标模板的特征表征能力；然后利用3个主干网络分别提取原始目标模板、超分辨率目标模板和数据增强目标模板的特征，并进行特征融合，同时在主干网络中应用了通道注意力模块和空间注意力模块，以提升特征提取能力；最后，将融合后的特征图与待搜索区域的特征图输入区域生成网络模块，得到目标跟踪信息。实验结果表明，该算法在OTB100数据集上的精确率为0.919、成功率为0.707，在VOT2018数据集上的准确率为0.642、鲁棒性为0.149，在实际场景中的运行速度每秒至少20次，说明该算法具有优异的跟踪性能，并且在各种复杂场景下都具有良好的鲁棒性。

Object tracking is of great significance in computer vision tasks. Recently, with the development of deep learning, the tracking algorithms based on Siamese networks have been extensively applied because of their excellent capabilities. However, the performance of the existing Siamese network modules degrades significantly when dealing with special situations such as large deformation of the target, low resolution, and complex background. To address these aforementioned issues, this paper proposed a tracking algorithm based on a multi-stream attention Siamese network. This algorithm first constructs super-resolution modules and data enhancement mo-dules, which performs super-resolution and data augmentation on the target templates, respectively, so as to improve the feature characterization ability of the target template. Then, the three backbone networks were used to extract the features of the original target template, the super-resolution target template, and the data augmentation target template, respectively, and their features were fused; simultaneously, the channel attention module and spatial attention module are applied in the backbone network to improve the feature extraction capability. Finally, the fused feature map and the feature map to be searched were input into the region proposal network module to obtain the target tracking information. The experimental results show that the algorithm achieved the precision of 0.919, the success of 0.707 on the OTB100 dataset and the accuracy of 0.642, the robustness of 0.149 on the VOT2018 dataset, with operation speed higher than 20 times per second in real scenarios, demonstrating the excellent tracking performance of the algorithm and excellent robustness in handling various complex scenarios.