Visual object tracking (VOT) is an essential component for many applications, such as autonomous driving or assistive robotics. However, recent works tend to develop accurate systems based on more computationally expensive feature extractors for better instance matching. In contrast, this work addresses the importance of motion prediction in VOT. We use an off-the-shelf object detector to obtain instance bounding boxes. Then, a combination of camera motion decouple and Kalman filter is used for state estimation. Although our baseline system is a straightforward combination of standard methods, we obtain state-of-the-art results. Our method establishes new state-of-the-art performance on VOT (VOT-2016 and VOT-2018). Our proposed method improves the EAO on VOT-2016 from 0.472 of prior art to 0.505, from 0.410 to 0.431 on VOT-2018. To show the generalizability, we also test our method on video object segmentation (VOS: DAVIS-2016 and DAVIS-2017) and observe consistent improvement.
翻译:视觉物体跟踪(VOT)是许多应用,如自主驾驶或辅助机器人等的基本组成部分。然而,最近的工程倾向于根据更昂贵的计算性能提取器来开发精确系统,以便进行更好的比对。与此相反,这项工作解决了VOT运动预测的重要性。我们使用现成的物体探测器来获取试测捆绑盒。然后,将照相机运动脱影和Kalman过滤器相结合用于国家估计。虽然我们的基线系统是标准方法的简单组合,但我们获得了最新的结果。我们的方法建立了VOT(VOT-2016和VOT-2018)的新的最新性能。我们提议的方法改进VOT-2016上的EAO,从以前的0.472改进到0.505,从VOT-2018的0.410到0.431。为了显示可概括性,我们还测试了视频物体分割的方法(VOS:DAVIS-2016和DAVIS-2017),并观察到了一致的改进。