期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 24, 期 4, 页码 1424-1435出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2015.2403231
关键词
Object tracking; deep feature learning; domain adaptation
资金
- Ministry of Education (MOE) [RG84/12, ARC28/14]
- Agency for Science, Technology and Research [PSF1321202099]
In this paper, we propose an approach to learn hierarchical features for visual object tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video sequences. The hierarchical features are learned via a two-layer convolutional neural network. Embedding the temporal slowness constraint in the stacked architecture makes the learned features robust to complicated motion transformations, which is important for visual object tracking. Then, given a target video sequence, we propose a domain adaptation module to online adapt the pre-learned features according to the specific target object. The adaptation is conducted in both layers of the deep feature learning module so as to include appearance information of the specific target object. As a result, the learned hierarchical features can be robust to both complicated motion transformations and appearance changes of target objects. We integrate our feature learning algorithm into three tracking methods. Experimental results demonstrate that significant improvement can be achieved using our learned hierarchical features, especially on video sequences with complicated motion transformations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据