Object detection is widely used in object tracking; anchor-free object tracking provides an end-to-end single-object-tracking approach. In this study, we propose a new anchor-free network, the Siamese center-prediction network (SiamCPN). Given the presence of referenced object features in the initial frame, we directly predict the center point and size of the object in subsequent frames in a Siamese-structure network without the need for perframe post-processing operations. Unlike other anchor-free tracking approaches that are based on semantic segmentation and achieve anchor-free tracking by pixel-level prediction, SiamCPN directly obtains all information required for tracking, greatly simplifying the model. A center-prediction sub-network is applied to multiple stages of the backbone to adaptively learn from the experience of different branches of the Siamese net. The model can accurately predict object location, implement appropriate corrections, and regress the size of the target bounding box. Compared to other leading Siamese networks, SiamCPN is simpler, faster, and more efficient as it uses fewer hyperparameters. Experiments demonstrate that our method outperforms other leading Siamese networks on GOT-10K and UAV123 benchmarks, and is comparable to other excellent trackers on LaSOT, VOT2016, and OTB-100 while improving inference speed 1.5 to 2 times.

目标检测广泛应用于目标跟踪。无锚对象跟踪提供了一种端到端的单对象跟踪方法。在这项研究中，我们提出了一个新的无锚网络，即暹罗中心预测网络（SiamCPN）。考虑到初始帧中存在引用的对象特征，我们可以在连体结构网络中直接预测后续帧中对象的中心点和大小，而无需进行逐帧后处理。与其他基于语义分割并通过像素级预测实现无锚跟踪的无锚跟踪方法不同，SiamCPN直接获取跟踪所需的所有信息，从而大大简化了模型。中心预测子网应用于骨干网的多个阶段，以从暹罗网络不同分支的经验中自适应学习。该模型可以准确地预测对象的位置，实施适当的校正并回归目标边界框的大小。与其他领先的Siamese网络相比，SiamCPN使用更少的超参数，因此更简单，更快且效率更高。实验表明，在GOT-10K和UAV123基准测试中，我们的方法优于其他领先的暹罗网络，可与LaSOT，VOT2016和OTB-100上的其他出色跟踪器相提并论，同时将推理速度提高了1.5到2倍。SiamCPN使用更少的超参数，因此更简单，更快且效率更高。实验表明，在GOT-10K和UAV123基准测试中，我们的方法优于其他领先的暹罗网络，可与LaSOT，VOT2016和OTB-100上的其他出色跟踪器相提并论，同时将推理速度提高了1.5到2倍。SiamCPN使用更少的超参数，因此更简单，更快且效率更高。实验表明，在GOT-10K和UAV123基准测试中，我们的方法优于其他领先的暹罗网络，可与LaSOT，VOT2016和OTB-100上的其他出色跟踪器相提并论，同时将推理速度提高了1.5到2倍。