Incremental learning for robust visual tracking
Incremental learning for robust visual tracking
复制标题
DOI：
10.1007/s11263-007-0075-7
复制
发表时间：
2008-05-01
影响因子：
19.5
通讯作者：
Yang, Ming-Hsuan
中科院分区：
文献类型：
--
作者：
Ross, David A.;Lim, Jongwoo;Yang, Ming-Hsuan
视觉跟踪本质上是处理随时间变化的非平稳图像流。虽然大多数现有的算法能够在受控环境中很好地跟踪对象，但它们通常在对象的外观或周围照明的显著变化的存在下失败。这种失败的一个原因是许多算法采用目标的固定外观模型。这种模型仅使用在跟踪开始之前可用的外观数据来训练，这在实践中限制了被建模的外观的范围，并且忽略了在跟踪期间变得可用的大量信息（诸如形状变化或特定照明条件）。在本文中，我们提出了一种跟踪方法，增量学习低维子空间表示，有效地适应在线目标的外观变化。基于主成分分析的增量算法的模型更新包括两个重要特征：用于正确更新样本均值的方法，以及用于确保较少建模能力被消耗以拟合较旧观测的遗忘因子。这两个功能都有助于提高整体跟踪性能。大量的实验表明，所提出的跟踪算法在室内和室外环境中的目标对象经历了很大的变化，姿态，规模和照明的有效性。
Visual tracking, in essence, deals with non-stationary image streams that change over time. While most existing algorithms are able to track objects well in controlled environments, they usually fail in the presence of significant variation of the object's appearance or surrounding illumination. One reason for such failures is that many algorithms employ fixed appearance models of the target. Such models are trained using only appearance data available before tracking begins, which in practice limits the range of appearances that are modeled, and ignores the large volume of information (such as shape changes or specific lighting conditions) that becomes available during tracking. In this paper, we present a tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target. The model update, based on incremental algorithms for principal component analysis, includes two important features: a method for correctly updating the sample mean, and a forgetting factor to ensure less modeling power is expended fitting older observations. Both of these features contribute measurably to improving overall tracking performance. Numerous experiments demonstrate the effectiveness of the proposed tracking algorithm in indoor and outdoor environments where the target objects undergo large changes in pose, scale, and illumination.