Sparse Hashing Tracking
Sparse Hashing Tracking
复制标题
稀疏散列跟踪
DOI：
10.1109/tip.2015.2509244
复制
发表时间：
2016
影响因子：
10.6
通讯作者：
Liu Luning
中科院分区：
文献类型：
--
作者：
Zhang Lihe;Lu Huchuan;Du D;an;Liu Luning
在本文中，我们提出了一种新的跟踪框架的基础上稀疏和歧视性哈希方法。与以前的工作不同，我们将对象跟踪视为二进制空间中的近似最近邻搜索过程。利用散列函数，可以将目标模板和候选者投影到汉明空间中，便于距离计算和跟踪效率。首先，我们综合类内和类间的信息来训练多个哈希函数，以获得更好的分类，而以往的跟踪方法中大多数分类器通常忽略了类间的相关性，这可能会导致不准确。然后，我们将稀疏度引入到哈希系数向量中进行动态特征选择，这对于选择具有鉴别力和稳定性的特征以适应跟踪过程中的视觉变化至关重要。在各种具有挑战性的序列上进行的大量实验表明，该算法的性能优于现有的方法。
In this paper, we propose a novel tracking framework based on a sparse and discriminative hashing method. Different from the previous work, we treat object tracking as an approximate nearest neighbor searching process in a binary space. Using the hash functions, the target templates and the candidates can be projected into the Hamming space, facilitating the distance calculation and tracking efficiency. First, we integrate both the inter-class and intra-class information to train multiple hash functions for better classification, while most classifiers in previous tracking methods usually neglect the inter-class correlation, which may cause the inaccuracy. Then, we introduce sparsity into the hash coefficient vectors for dynamic feature selection, which is crucial to select the discriminative and stable features to adapt to visual variations during the tracking process. Extensive experiments on various challenging sequences show that the proposed algorithm performs favorably against the state-of-the-art methods.