| 基于最稳定极值区域方法的目标检测与跟踪 |
| |
| 引用本文： | 连宝超,赵晓林,胡峰,周子啸,张利.基于最稳定极值区域方法的目标检测与跟踪[J].电视技术,2009,33(10). |
| |
| 作者姓名： | 连宝超 赵晓林 胡峰 周子啸 张利 |
| |
| 作者单位： | 1. 清华大学微电子所,北京,100084
2. 清华大学电子工程系,北京,100084 |
| |
| 基金项目： | 国家自然科学基金项目 |
| |
| 摘 要： | 针对非刚体目标的精确实时跟踪问题,提出了一种融合先验形状信患的基于最稳定极值区域(MSER)检测器的跟踪算法.首先,利用训练样本建立目标颜色特征的混合模型,生成目标统计颜色概率图,为最大稳定区域方法提供概率统计依据.其次,利用基于最稳定极值区域方法给出最稳定的分割结果.最后,利用训练样本得到目标的先验动态形状模型,并且融合目标形状信息与通过MSER算法生成的稳定区域信息,去除虚假分割结果,提高目标检测精度与跟踪性能.实验结果证明,该算法能在视频序列图像中有效检测并跟踪目标.
|
| 关 键 词： | 最稳定极值区域 主分量分析 目标检测 目标跟踪 |
Objects Detecting and Tracking Based on MSER |
| |
| LIAN Bao-chao,ZHAO Xiao-lin,HU Feng,ZHOU Zi-xiao,ZHANG Li.Objects Detecting and Tracking Based on MSER[J].Tv Engineering,2009,33(10). |
| |
| Authors: | LIAN Bao-chao ZHAO Xiao-lin HU Feng ZHOU Zi-xiao ZHANG Li |
| |
| Affiliation: | LIAN Bao-chaoa,ZHAO Xiao-linb,HU Fengb,ZHOU Zi-xiaoa,ZHANG Lib(a.Institute of Microelectronics,b.Department of Electronic Engineering,Tsinghua University,Beijing 100084,China ) |
| |
| Abstract: | An exact non-grid object detecting and tracking algorithm is proposed which combines the Maximally Stable Extremal Region(MSER) with the object shape prior knowledge.The first step of the algorithm is the calculation of multivariate Gaussians of color likelihoods which will be passed to the MSER.Secondly, based on analysis of MSER, the maximally stable boundaries are exploited by finding the connected regions of interest.Finally, by obtaining the object shape prior model from training set using Principal Co... |
| |
| Keywords: | MSER PCA object detecting multiple object tracking |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
