基于字典学习的实时运动目标跟踪算法 |
| |
引用本文: | 周安,蒋辉,余晋刚,田金文. 基于字典学习的实时运动目标跟踪算法[J]. 战术导弹技术, 2014, 0(4): 99-104 |
| |
作者姓名: | 周安 蒋辉 余晋刚 田金文 |
| |
作者单位: | 华中科技大学自动化学院;北京机电工程研究所; |
| |
基金项目: | 国家自然科学基金资助项目(61273279) |
| |
摘 要: | 采用提取图像的尺度不变特征可以获得较好的匹配跟踪效果,但该特征提取方法比较耗时。针对这一问题,提出了一种鲁棒的实时目标跟踪方法。该方法通过提取目标的多尺度平移、旋转特征来构建字典,提高了算法的鲁棒性。利用所构建的字典来表示待跟踪目标集特征,查找与目标模板最近邻的待跟踪目标,即可确定跟踪的最终结果。试验结果表明,这种基于字典学习的实时跟踪算法可以鲁棒实时地跟踪单目标。
|
关 键 词: | 目标跟踪 字典学习 实时跟踪 |
Robust Real-time Object Tracking Based on Dictionary Learning |
| |
Affiliation: | Zhou An , Jiang Hui, Yu Jingang , Tian Jinwen ( 1. College of Automation, Huazhong University of Science and Technology, Hubei 430074, China; 2. Beijing Electro-mechanical Engineering Institute, Beijing 100074, China) |
| |
Abstract: | Through the matching of scale-invariant visual features, satisfactory tracking results can usual- ly be obtained. However, this approach computationally is very expensive. To overcome the challenging problem, a real-time object tracking method is presented based on feature matching. In the proposed ap- proach, multi-scale translation and rotation invariant features are extracted to build a dictionary with good robustness. And then, the target is represented by coding under this dictionary. Finally, the tracking re- sult is obtained by exhaustively searching for the one that best matches the target model among all the candidates. Experiment results show that this method can achieve real-time and robust tracking target. |
| |
Keywords: | object tracking dictionary learning real-time tracking |
本文献已被 CNKI 维普 等数据库收录! |
|