Compressive sensing based visual tracking using multi-task sparse learning method
| Autor: | Wei-Ping Zhu, Bin Kang, Linghua Zhang, Daniel Pak Kong Lun |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
business.industry
Computer science Pattern recognition 02 engineering and technology Sparse approximation Visualization Sparse learning Compressed sensing Robustness (computer science) 020204 information systems 0202 electrical engineering electronic engineering information engineering Eye tracking 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Sparse matrix |
| Zdroj: | WCSP |
| DOI: | 10.1109/wcsp.2016.7752465 |
| Popis: | In this paper, we propose a compressive sensing based framework for robust visual tracking. As a key part of the tracking framework, a new multi-task sparse learning method is designed to estimate the observation likelihood in order to determine the best target. Compared with the traditional multi-task sparse learning method, our method uses compressed appearance features to achieve multi-task sparse representation. Experimental results show that the proposed visual tracking framework can achieve a better tracking performance than state-of-the-art tracking methods with a significantly reduced computational complexity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|