Robust Visual Tracking via Multiple Kernel Boosting With Affinity Constraints
Robust Visual Tracking via Multiple Kernel Boosting With Affinity Constraints
复制标题
DOI：
10.1109/tcsvt.2013.2276145
复制
发表时间：
2014-02
影响因子：
8.4
通讯作者：
F. Yang;Huchuan Lu;Ming-Hsuan Yang
中科院分区：
文献类型：
--
作者：
F. Yang;Huchuan Lu;Ming-Hsuan Yang
我们提出了一种新的算法，通过扩展多核学习框架，提高特征和内核的最佳组合，从而有效地促进复杂场景中的鲁棒视觉跟踪。虽然空间信息已被考虑到在传统的多核学习算法，我们施加新的亲和约束，从不同的角度利用本地的支持向量。与文献中现有的方法相比，该算法是在概率框架中制定的，可以有效地计算。在具有挑战性的数据集上进行的大量实验与最先进的算法进行了比较，证明了该算法使用多核提升和亲和约束的优点。
We propose a novel algorithm by extending the multiple kernel learning framework with boosting for an optimal combination of features and kernels, thereby facilitating robust visual tracking in complex scenes effectively and efficiently. While spatial information has been taken into account in conventional multiple kernel learning algorithms, we impose novel affinity constraints to exploit the locality of support vectors from a different view. In contrast to existing methods in the literature, the proposed algorithm is formulated in a probabilistic framework that can be computed efficiently. Numerous experiments on challenging data sets with comparisons to state-of-the-art algorithms demonstrate the merits of the proposed algorithm using multiple kernel boosting and affinity constraints.