论文标题
视觉对象跟踪中的运动预测
Motion Prediction in Visual Object Tracking
论文作者
论文摘要
视觉对象跟踪（fot）是许多应用程序的重要组成部分，例如自动驾驶或辅助机器人技术。但是，最近的作品倾向于基于更昂贵的功能提取器来开发准确的系统，以提供更好的实例匹配。相比之下，这项工作探讨了投票中运动预测的重要性。我们使用现成的对象检测器获取实例边界框。然后，使用摄像机运动截发和卡尔曼过滤器的组合进行状态估计。尽管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。我们的方法建立了在投票（FOT-2016和FOT-2018）上的最新性能。我们提出的方法将EAO在2016年的EAO从先前的0.472提高到0.505，从0.410提高到2018年的0.431。为了显示概括性，我们还测试了视频对象细分（VOS：Davis-2016和Davis-2017）的方法，并观察到一致的改进。
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.
