IEEE Trans Pattern Anal Mach Intell. 2011 Aug;33(8):1619-32. doi: 10.1109/TPAMI.2010.226. Epub 2010 Dec 23.
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.
在本文中，我们解决了在给定第一帧中对象位置且没有其他信息的情况下跟踪视频中对象的问题。最近，一类称为“基于检测的跟踪”的跟踪技术已被证明可以在实时速度下取得有希望的结果。这些方法以在线方式训练判别分类器，以将对象与背景分开。该分类器通过使用当前跟踪器状态从当前帧中提取正例和负例来自适应地进行训练。因此，跟踪器的微小误差可能导致训练示例的错误标记，从而降低分类器的性能并导致漂移。在本文中，我们表明，使用多实例学习（MIL）代替传统的监督学习可以避免这些问题，因此可以使用更少的参数调整来实现更稳健的跟踪器。我们提出了一种新颖的在线 MIL 算法，用于对象跟踪，该算法在实时性能方面取得了卓越的效果。我们在一些具有挑战性的视频剪辑上进行了彻底的实验（包括定性和定量）。
