Abstract
In this paper, a method for real-time tracking of moving targets is proposed. The particle filter and mean shift technical for color-based tracking is used. The traditional tracker always focuses on how to track with the object robustly in a short period of time. Most of them modify the model after the tracking is finished in current frame. But in long time tracking, the object model is changing continuously. Under the mean shift tracking framework, particle filter technical is used to predict the object model, and track with the new one. With this method, we don't need to fix a threshold to modify the model manually. The experimental results show that out methods has better performance than the traditional kernel based tracker.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09 |
| DOIs | |
| Publication status | Published - 2009 |
| Event | 2009 2nd International Congress on Image and Signal Processing, CISP'09 - Tianjin, China Duration: 17 Oct 2009 → 19 Oct 2009 |
Publication series
| Name | Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09 |
|---|
Conference
| Conference | 2009 2nd International Congress on Image and Signal Processing, CISP'09 |
|---|---|
| Country/Territory | China |
| City | Tianjin |
| Period | 17/10/09 → 19/10/09 |
Keywords
- Component
- Mean shift
- Model prediction
- Object tracking
- Particle filter
Fingerprint
Dive into the research topics of 'Object tracking with mean shift and model prediction'. Together they form a unique fingerprint.Cite this
Zhou, B., Wang, J. Z., Li, J., & Shen, W. (2009). Object tracking with mean shift and model prediction. In Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09 Article 5303702 (Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09). https://doi.org/10.1109/CISP.2009.5303702