원문정보
초록
영어
Features for representing the target are the fundamental ingredient when constructing the appearance model in the tracking problem. Only one type of features is utilized to represent the target in most current algorithms. However, the limited representation of a single feature might not resist all appearance changes of the target during the tracking process. To cope with this problem, we propose a novel tracking algorithm - Mean Kernel Tracker (MKT) - to robustly locate the object. The MKT combines three complementary features - Color, HOG (Histogram of Oriented Gradient) and LBP (Local Binary Pattern) - to represent the target. And Extensive experiments on public benchmark sequences show MKT performs favorably against several state-of-the-art algorithms.
목차
1. Introduction
2. Mean Kernel Learning
3. Details of the Implementation
3.1. Preparation of Training Sets
3.2. The Features for Tracking
3.3. Parameter Settings
4. Experiments
5. Conclusion
References