| 融合纹理特征的Mean-shift抗遮挡目标跟踪算法 |
| |
| 引用本文： | 曹洁,付德强.融合纹理特征的Mean-shift抗遮挡目标跟踪算法[J].兰州理工大学学报,2011,37(5):88-91. |
| |
| 作者姓名： | 曹洁 付德强 |
| |
| 作者单位： | 兰州理工大学电气工程与信息工程学院,甘肃兰州,730050 |
| |
| 基金项目： | 甘肃省自然科学基金(1010RJZA046); 甘肃省教育厅研究生导师基金(0914ZTB003) |
| |
| 摘 要： | 针对传统Mean-shift算法仅利用颜色特征,当场景中合有目标颜色相近的物体时,易发生误跟踪,且在目标被遮挡的情况下,无法进行有效的跟踪,提出一种融合目标纹理特征的抗遮挡跟踪算法.同时实时更新模板,并通过Kalman滤波估计目标的状态,在目标被遮挡的情况下进行估计预测,提出一种遮挡因子作为目标遮挡的判据,严重遮挡时,...
|
| 关 键 词： | 目标跟踪 Mean-shift算法 纹理特征 遮挡因子 |
Anti-occlusion object tracking algorithm based on fused texture feature Mean-shift |
| |
| CAO Jie,FU De-qiang.Anti-occlusion object tracking algorithm based on fused texture feature Mean-shift[J].Journal of Lanzhou University of Technology,2011,37(5):88-91. |
| |
| Authors: | CAO Jie FU De-qiang |
| |
| Institution: | CAO Jie,FU De-qiang(College of Electrical and Information Engineering,Lanzhou Univ.of Tech.,Lanzhou 730050,China) |
| |
| Abstract: | In traditional Mean-shift algorithm only the color features of object was used.When the scene contained a object with color similar to the tracked object color,an error tracking would happen.When the object was occluded,the object could not be tracked effectively.An anti-occlusion object tracking method with fused texture features of the object was proposed.Meantime,the template was updated,and the Kalman filter was used for object estimation and prediction when the object was occluded.An object-occlusion f... |
| |
| Keywords: | object tracking Mean-shift algorithm texture feature occlusion factor |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
