We propose SiamGauss, a Siamese region proposal network with a Gaussian head for single-target visual object tracking for aerial benchmarks. Visual tracking in aerial videos faces unique challenges due to the large field of view resulting in small size objects, similar looking objects (confusers) in close proximity, occlusions, and fast motion due to simultaneous object and camera motion. In Siamese tracking, a cross-correlation ration is performed in the embedding space to obtain a similarity map of the target within a search frame, which is then used to localize the target. The proposed Gaussian head helps suppress the activation produced in the similarity map on confusers present in the search frame during training while boosting the confidence on the target. This activation suppression improves the confuser awareness of our tracker. In addition, improving the activation on the target helps maintain tracking consistency in fast motion. Our proposed Gaussian head is only applied during training and introduces no additional computational overhead during inference while tracking. Thus, SiamGauss achieves fast runtime performance. We evaluate our method on multiple aerial benchmarks showing that SiamGauss performs favorably with state-of-the-art trackers while rating at a frame rate of 96 frames per second.

中文翻译：

---

SiamGauss：具有高斯头的 Siamese region proposal 网络，用于视觉对象跟踪

我们提出了 SiamGauss，一个具有高斯头的 Siamese 区域提议网络，用于航空基准的单目标视觉对象跟踪。航拍视频中的视觉跟踪面临着独特的挑战，因为大视场会导致小尺寸物体、外观相似的物体（混淆器）靠近、遮挡以及由于物体和相机同时运动而导致的快速运动。在连体跟踪中，在嵌入空间中执行互相关比以获得目标在搜索框架内的相似度图，然后用于定位目标。所提出的高斯头有助于抑制在训练期间出现在搜索框架中的混淆器的相似度图中产生的激活，同时提高对目标的置信度。这种激活抑制提高了我们跟踪器的混淆器意识。此外，提高对目标的激活有助于保持快速运动中的跟踪一致性。我们提出的高斯头仅在训练期间应用，并且在跟踪期间的推理期间不会引入额外的计算开销。因此，SiamGauss 实现了快速的运行时性能。我们在多个空中基准测试中评估了我们的方法，表明 SiamGauss 在最先进的跟踪器上表现出色，同时以每秒 96 帧的帧速率进行评级。