Name
Abstract | ||
|---|---|---|
This paper presents an adaptive tracking algorithm by learning hybrid object templates online in video. The templates consist of multiple types of features, each of which describes one specific appearance structure, such as flatness, texture, or edge/corner. Our proposed solution consists of three aspects. First, in order to make the features of different types comparable with each other, a unified statistical measure is defined to select the most informative features to construct the hybrid template. Second, we propose a simple yet powerful generative model for representing objects. This model is characterized by its simplicity since it could be efficiently learnt from the currently observed frames. Last, we present an iterative procedure to learn the object template from the currently observed frames, and to locate every feature of the object template within the observed frames. The former step is referred to as feature pursuit, and the latter step is referred to as feature alignment, both of which are performed over a batch of observations. We fuse the results of feature alignment to locate objects within frames. The proposed solution to object tracking is in essence robust against various challenges, including background clutters, low-resolution, scale changes, and severe occlusions. Extensive experiments are conducted over several publicly available databases and the results with comparisons show that our tracking algorithm clearly outperforms the state-of-the-art methods. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/TCSVT.2011.2129410 | IEEE Trans. Circuits Syst. Video Techn. |
Keywords | Field | DocType |
hybrid object templates online,proposed solution,hybrid template,former step,adaptive tracking algorithm,feature alignment,learning hybrid template online,adaptive object tracking,observed frame,informative feature,object template,tracking algorithm,object tracking,matching pursuit,template matching,visualization,indexing terms,feature extraction,learning artificial intelligence,bismuth,low resolution,iterative methods | Flatness (systems theory),Matching pursuit,Computer vision,Pattern recognition,Iterative method,Visualization,Computer science,Feature extraction,Video tracking,Artificial intelligence,Template,Generative model | Journal |
Volume | Issue | ISSN |
21 | 11 | 1051-8215 |
Citations | PageRank | References |
21 | 0.68 | 19 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaobai Liu | 1 | 800 | 40.79 |
| Liang Lin | 2 | 3007 | 151.07 |
| Shuicheng Yan | 3 | 9701 | 359.54 |
| Hai Jin | 4 | 6544 | 644.63 |
| Wenbin Jiang | 5 | 355 | 36.55 |