With the rapid advancement of satellite technology, satellite video has emerged as a key method for acquiring dynamic terrestrial information, facilitating multiple object tracking (MOT). Satellites are capable of surveying vast urban landscapes, yet the observed objects are small and dispersed among complex interference from the background, heightening the challenges in detection and association tasks for object tracking. However, current trackers often dissociate the classification task from the localization task, leading to drift in tiny object detection (TOD), and rely on prior knowledge for clue ranking, limiting model robustness. In this article, we introduce the graph-based multiclue fusion tracker (GMFTracker). Initially, we introduce a sparse sampling-based feature map correction approach to rectify the misalignment between the classification and localization feature maps. Furthermore, we developed graph neural networks (GNNs) for object relationship modeling, free from presuppositions, to tackle association challenges using relational features. GMFTracker was rigorously tested on VISO, CGSTL, and TinyPerson datasets, demonstrating its competitive performance relative to contemporary studies.

中文翻译：

---

使用基于图的多线索融合跟踪器进行卫星视频中的多目标跟踪


随着卫星技术的快速进步，卫星视频已成为获取动态地面信息、促进多目标跟踪（MOT）的关键方法。卫星能够勘测广阔的城市景观，但观测到的物体很小且分散在背景的复杂干扰中，这加大了物体跟踪的检测和关联任务的挑战。然而，当前的跟踪器经常将分类任务与定位任务分离，导致微小物体检测（TOD）的漂移，并依赖先验知识进行线索排序，限制了模型的鲁棒性。在本文中，我们介绍了基于图的多线索融合跟踪器（GMFTracker）。最初，我们引入了一种基于稀疏采样的特征图校正方法来纠正分类和定位特征图之间的不对齐。此外，我们开发了用于对象关系建模的图神经网络（GNN），无需预设，即可使用关系特征来应对关联挑战。 GMFTracker 在 VISO、CGSTL 和 TinyPerson 数据集上进行了严格测试，证明了其相对于当代研究的竞争性能。