In this paper, we propose a constrained graph labeling algorithm for visual tracking where nodes denote superpixels and edges encode the underlying spatial, temporal, and appearance fitness constraints. First, the spatial smoothness constraint, based on a transductive learning method, is enforced to leverage the latent manifold structure in feature space by investigating unlabeled superpixels in the current frame. Second, the appearance fitness constraint, which measures the probability of a superpixel being contained in the target region, is developed to incrementally induce a long-term appearance model. Third, the temporal smoothness constraint is proposed to construct a short-term appearance model of the target, which handles the drastic appearance change between consecutive frames. All these three constraints are incorporated in the proposed graph labeling algorithm such that induction and transduction, short- and long-term appearance models are combined, respectively. The foreground regions inferred by the proposed graph labeling method are used to guide the tracking process. Tracking results, in turn, facilitate more accurate online update by filtering out potential contaminated training samples. Both quantitative and qualitative evaluations on challenging tracking data sets show that the proposed constrained tracking algorithm performs favorably against the state-of-the-art methods.

中文翻译：

---

约束超像素跟踪

在本文中，我们提出了一种用于视觉跟踪的约束图标记算法，其中节点表示超像素，边缘编码潜在的空间，时间和外观适应性约束。首先，通过研究当前帧中未标记的超像素，强制执行基于跨导学习方法的空间平滑约束，以利用特征空间中的潜在流形结构。其次，开发了外观适合度约束（用于衡量目标区域中包含超像素的概率），以逐步引入长期外观模型。第三，提出了时间平滑约束来构造目标的短期外观模型，该模型可以处理连续帧之间的剧烈外观变化。所有这三个约束条件都纳入了提出的图形标记算法中，从而分别组合了归纳和转导，短期和长期外观模型。通过提出的图形标注方法推断出的前景区域用于指导跟踪过程。跟踪结果又通过滤除潜在的受污染的训练样本，促进了更准确的在线更新。对具有挑战性的跟踪数据集的定量和定性评估都表明，所提出的约束跟踪算法相对于最新方法具有良好的性能。跟踪结果又通过滤除潜在的受污染的训练样本，促进了更准确的在线更新。对具有挑战性的跟踪数据集的定量和定性评估都表明，所提出的约束跟踪算法相对于最新方法具有良好的性能。跟踪结果又通过滤除潜在的受污染的训练样本，促进了更准确的在线更新。对具有挑战性的跟踪数据集的定量和定性评估都表明，所提出的约束跟踪算法相对于最新方法具有良好的性能。