| 基于双边滤波的协方差目标跟踪算法 |
| |
| 引用本文： | 谢英红,李凌,何宇清.基于双边滤波的协方差目标跟踪算法[J].电子测量与仪器学报,2016,30(8):1282-1287. |
| |
| 作者姓名： | 谢英红 李凌 何宇清 |
| |
| 作者单位： | 1. 天津大学电子信息工程学院 天津300072;沈阳大学信息工程学院 沈阳110044;2. 唐山师范学院 唐山063000;3. 天津大学电子信息工程学院 天津300072 |
| |
| 基金项目： | 国家自然科学基金(61503274)，国家自然科学基金(61472274)，辽宁省教育厅科学技术研究项目(L2014481)，辽宁省博士启动基金(201501090) |
| |
| 摘 要： | 现有的使用协方差建模的目标跟踪方法在目标形变或是光照变化较大的情况下,达不到理想的跟踪效果。在分析目前协方差建模目标跟踪方法缺点的基础上,提出一种融合双边滤波的协方差目标跟踪算法。首先,将待跟踪图像进行双边滤波,提取滤波后的图像特征构建协方差特征矩阵作为跟踪模板。其次,由于协方差矩阵为对称正定流形,服从对数-欧几里德黎曼度量。在此度量下,构建了目标协方差矩阵相似性度量和模板更新策略。各种条件下的实验结果表明,新构建的基于双边滤波的协方差特征矩阵对目标形变和光照变化有更好的适应性。
|
| 关 键 词： | 目标跟踪 双边滤波 协方差矩阵 对数-欧几里德 黎曼度量 |
Covariance object tracking algorithm based on bilateral filtering |
| |
| Xie Yinghong,Li Ling and He Yuqing.Covariance object tracking algorithm based on bilateral filtering[J].Journal of Electronic Measurement and Instrument,2016,30(8):1282-1287. |
| |
| Authors: | Xie Yinghong Li Ling and He Yuqing |
| |
| Affiliation: | 1. School of Electronic Informatin Engineering, Tianjin University, Tianjin 300072, China;
2. School of Information Engineering, Shenyang University, Shenyang 110044, China,Tangshan Normal University, Tangshan 036000, China and School of Electronic Informatin Engineering, Tianjin University, Tianjin 300072, China |
| |
| Abstract: | The existing object tracking method using covariance modeling is hard to reach the desired tracking performance when the deformation of moving target and illumination changes are drastic. Based on the analysis of the shortcoming of target tracking method using covariance modeling, a covariance object tracking algorithm based on bilateral filtering is proposed. Firstly, the algorithm deals the image to be tracked with bilateral filtering, and extracts the needed features of filtered image to construct covariance matrix as tracking model. Secondly, covariance matrix is positive symmetric manifold, so it obeys log Euclidean Riemannian metric. Under this metric, the similarity measure for object covariance matrix and the model updating strategy are constructed. Extensive experiments show that the proposed covariance matrix based on bilateral filtering has better adaptability for object deformation and illumination changes. |
| |
| Keywords: | object tracking bilateral filtering covariance matrix log-Euclidean Riemannian metric |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《电子测量与仪器学报》浏览原始摘要信息 |
|
点击此处可从《电子测量与仪器学报》下载全文 |
|
