a mean shift algorithm based on modified parzen window for small target tracking
文献类型：会议论文
| 作者 | Chen Jianjun ; An Guocheng ; Zhang Suofei ; Wu Zhenyang |
| 出版日期 | 2010 |
| 会议名称 | 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 |
| 会议日期 | March 14, |
| 会议地点 | Dallas, TX, United states |
| 关键词 | Algorithms Graphic methods Interpolation Signal processing Vector quantization Video recording |
| 页码 | 1166-1169 |
| 英文摘要 | This paper addresses the problem of small scale target tracking. The divided-by-zero problem in the weight computation of mean shift algorithm and its associated tracking interrupt problem are presented. To tackle these problems, the Parzen window density estimation method is modified to interpolate the histogram of the target candidate. Then the Kullback-Leibler distance is employed as a new similarity measure between the target model and the target candidate. Its corresponding weight computation and new location expressions are derived. On the basis of these works, we propose a new small target tracking algorithm using mean shift framework. The tracking experiments for real world video sequences show that the proposed algorithm can track the target successively and accurately. It can successfully track very small targets with only 6x12 pixels. ©2010 IEEE. |
| 收录类别 | EI |
| 会议主办者 | The Institute of Electrical and Electronics Engineers; Signal Processing Society |
| 会议录 | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
 |
| 会议录出版地 | United States |
| 语种 | 英语 |
| ISSN号 | 15206149 |
| ISBN号 | 9781420000000 |
| 源URL | [http://124.16.136.157/handle/311060/8606]  |
| 专题 | 软件研究所_软件所图书馆_2010软件所会议论文 |
| 推荐引用方式 GB/T 7714 | Chen Jianjun,An Guocheng,Zhang Suofei,et al. a mean shift algorithm based on modified parzen window for small target tracking[C]. 见:2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010. Dallas, TX, United states. March 14,. |
入库方式： OAI收割
来源：软件研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。