Real-Time Object Tracking Via Online Discriminative Feature Selection
Real-Time Object Tracking Via Online Discriminative Feature Selection
复制标题
DOI：
10.1109/tip.2013.2277800
复制
发表时间：
2013-12
影响因子：
10.6
通讯作者：
Kaihua Zhang;Lei Zhang;Ming-Hsuan Yang
中科院分区：
文献类型：
--
作者：
Kaihua Zhang;Lei Zhang;Ming-Hsuan Yang
大多数检测跟踪算法训练判别分类器将目标对象从其周围背景中分离出来。在此设置中，当噪声样本未被正确采样时，它们可能被包括在内，从而导致视觉漂移。多实例学习（MIL）范式最近已被应用于缓解这个问题。然而，实例标签的重要先验信息和最正确的正实例（即，当前帧中的跟踪结果）可以使用比MIL方法简单得多的新公式来利用。在本文中，我们表明，将这些先验信息集成到一个监督学习算法可以更有效地处理视觉漂移比现有的MIL跟踪器。我们提出了一个在线判别特征选择算法，优化目标函数的最陡上升方向相对于正样本，而在最陡下降方向相对于负的。因此，经过训练的分类器直接将其得分与样本的重要性相结合，从而产生更鲁棒和更有效的跟踪器。大量的实验评估与国家的最先进的算法上具有挑战性的序列证明了所提出的算法的优点。
Most tracking-by-detection algorithms train discriminative classifiers to separate target objects from their surrounding background. In this setting, noisy samples are likely to be included when they are not properly sampled, thereby causing visual drift. The multiple instance learning (MIL) paradigm has been recently applied to alleviate this problem. However, important prior information of instance labels and the most correct positive instance (i.e., the tracking result in the current frame) can be exploited using a novel formulation much simpler than an MIL approach. In this paper, we show that integrating such prior information into a supervised learning algorithm can handle visual drift more effectively and efficiently than the existing MIL tracker. We present an online discriminative feature selection algorithm that optimizes the objective function in the steepest ascent direction with respect to the positive samples while in the steepest descent direction with respect to the negative ones. Therefore, the trained classifier directly couples its score with the importance of samples, leading to a more robust and efficient tracker. Numerous experimental evaluations with state-of-the-art algorithms on challenging sequences demonstrate the merits of the proposed algorithm.