Robust Object Tracking with Online Multiple Instance Learning
Robust Object Tracking with Online Multiple Instance Learning
复制标题
DOI：
10.1109/tpami.2010.226
复制
发表时间：
2011-08-01
影响因子：
23.6
通讯作者：
Belongie, Serge
中科院分区：
文献类型：
--
作者：
Babenko, Boris;Yang, Ming-Hsuan;Belongie, Serge
在本文中，我们解决的问题，跟踪一个对象在视频给定的位置在第一帧，没有其他信息。最近，一类被称为“检测跟踪”的跟踪技术已被证明在实时速度下给出有希望的结果。这些方法以在线方式训练判别分类器以将对象与背景分离。该分类器通过使用当前跟踪器状态来自举以从当前帧提取正面和负面示例。因此，跟踪器中的轻微不准确可能导致错误标记的训练示例，这会降低分类器的性能并可能导致漂移。在本文中，我们表明，使用多实例学习（MIL），而不是传统的监督学习避免了这些问题，因此可以导致一个更强大的跟踪器，更少的参数调整。我们提出了一种新的在线MIL算法的目标跟踪，实现了上级的结果与实时性能。我们提出了彻底的实验结果（定性和定量）对一些具有挑战性的视频剪辑。
In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called "tracking by detection" has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.