| 基于特征分组的在线目标跟踪算法 |
| |
| 引用本文： | 姜明新.基于特征分组的在线目标跟踪算法[J].大连理工大学学报,2013,53(5):755-759. |
| |
| 作者姓名： | 姜明新 |
| |
| 作者单位： | 大连理工大学信息与通信工程学院;大连民族学院信息与通信工程学院 |
| |
| 基金项目： | 国家自然科学基金资助项目(61172058);中央高校基本科研业务费专项资金资助项目(DC10010103);辽宁省教育厅资助项目(L2012476) |
| |
| 摘 要： | 在线目标跟踪是计算机视觉领域的一个具有挑战性的问题.提出了一种基于特征分组的在线目标跟踪算法.首先,利用像素点在多帧的方差对模板库中的目标模板进行特征分组.然后,利用主要特征图像和次要特征图像学习投影矩阵P,对样本进行投影.最后,利用最小误差法得出当前帧的跟踪结果.与其他典型算法相比,该算法对目标的异常变化具有很强的鲁棒性.
|
| 关 键 词： | 在线目标跟踪 线性子空间学习 特征分组 模板更新 |
Online object tracking algorithm based on feature grouping |
| |
| JIANG,Ming-xin.Online object tracking algorithm based on feature grouping[J].Journal of Dalian University of Technology,2013,53(5):755-759. |
| |
| Authors: | JIANG Ming-xin |
| |
| Institution: | JIANG Ming-xin;WANG Hong-yu;School of Information and Communication Engineering,Dalian University of Technology;College of Information & Communication Engineering,Dalian Nationalities University; |
| |
| Abstract: | Online object tracking is a challenging issue in computer vision. An online object tracking algorithm based on feature grouping is proposed. Firstly, the object templates in template base are grouped by computing the variance of the pixels in multiple frames. Then, the projection matrix P is learned based on the more discriminative image and the less discriminative image, and the samples are projected. Finally, tracking results of the current frame are performed by minimum error. Compared with other popular methods, the proposed method has strong robustness to abnormal changes. |
| |
| Keywords: | online object tracking linear subspace learning feature grouping template updating |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《大连理工大学学报》浏览原始摘要信息 |
| 点击此处可从《大连理工大学学报》下载免费的PDF全文 |
