Robust Visual Tracking via Coupled Randomness
Robust Visual Tracking via Coupled Randomness
复制标题
DOI：
10.1587/transinf.2014edp7210
复制
发表时间：
2015-05
期刊：
影响因子：
--
通讯作者：
Chao Zhang-;Y. Yamagata;T. Akashi
中科院分区：
文献类型：
--
作者：
Chao Zhang-;Y. Yamagata;T. Akashi
任意目标的跟踪算法是计算机视觉领域的研究热点。在开始时，初始化的边界框作为输入。在此之后，算法需要在后续帧中实时跟踪目标。检测跟踪是在线跟踪的主要研究方向之一。然而，为了提高性能，仍然存在两个问题。1)有限的处理时间要求模型从训练样本中提取低维和区分性特征。2)模型要求能够平衡先验和新目标的外观信息，以保持重定位能力并避免漂移问题。在本文中，我们提出了一个实时跟踪算法称为耦合随机跟踪（CRT），重点是处理这两个问题。一个随机性表示随机投影，另一个随机性表示在线随机森林（ORF）。在CRT中，灰度特征被一个稀疏的测量矩阵压缩，并使用ORF在线训练样本序列。在训练过程中，我们引入了一个树丢弃策略，帮助ORF适应快速的外观变化所造成的光照，遮挡等，我们的方法可以不断适应目标的最新外观变化，同时保持先验的外观信息。实验结果表明，我们的算法执行鲁棒性与许多公开可用的基准视频，并优于几个国家的最先进的算法。此外，我们的算法可以很容易地利用到一个并行程序。关键词：在线跟踪，特征压缩，在线随机森林
Tracking algorithms for arbitrary objects are widely researched in the field of computer vision. At the beginning, an initialized bounding box is given as the input. After that, the algorithms are required to track the objective in the later frames on-the-fly. Tracking-by-detection is one of the main research branches of online tracking. However, there still exist two issues in order to improve the performance. 1) The limited processing time requires the model to extract low-dimensional and discriminative features from the training samples. 2) The model is required to be able to balance both the prior and new objectives’ appearance information in order to maintain the relocation ability and avoid the drifting problem. In this paper, we propose a real-time tracking algorithm called coupled randomness tracking (CRT) which focuses on dealing with these two issues. One randomness represents random projection, and the other randomness represents online random forests (ORFs). In CRT, the grayscale feature is compressed by a sparse measurement matrix, and ORFs are used to train the sample sequence online. During the training procedure, we introduce a tree discarding strategy which helps the ORFs to adapt fast appearance changes caused by illumination, occlusion, etc. Our method can constantly adapt to the objective’s latest appearance changes while keeping the prior appearance information. The experimental results show that our algorithm performs robustly with many publicly available benchmark videos and outperforms several state-of-the-art algorithms. Additionally, our algorithm can be easily utilized into a parallel program. key words: online tracking, feature compression, online random forests