| 基于鲁棒统计量的运动检测与目标跟踪策略 |
| |
| 引用本文： | 胡玉锁,陈会勇,陈宗海.基于鲁棒统计量的运动检测与目标跟踪策略[J].系统仿真学报,2006,18(2):439-443. |
| |
| 作者姓名： | 胡玉锁 陈会勇 陈宗海 |
| |
| 作者单位： | 中国科学技术大学多媒体计算与通信教育部-微软重点实验室,中国科学技术大学自动化系,安徽,合肥,230027 |
| |
| 摘 要： | 提出了一种基于鲁棒统计量的运动检测方法。该方法通过对全局运动的鲁棒估计和对残差进行假设检验的方法来检测运动物体区域。为了消除遮挡效应的影响,提高算法的精度,在检测过程中,利用双向运动估计的方法来对残差进行归一化。在此基础上,提出了一种鲁棒主动轮廓模型,用于跟踪运动物体轮廓,并采用LevelSet方法对该模型进行求解。实际视频的实验结果表明,该方法能够可靠、准确的检测与跟踪运动物体。
|
| 关 键 词： | 机器视觉 运动检测 物体跟踪 鲁棒估计 主动轮廓模型 |
| 文章编号： | 1004-731X（2006）02-0439-05 |
| 收稿时间： | 2004-11-17 |
| 修稿时间： | 2005-09-05 |
Novel Strategy of Motion Detection and Object Tracking Based on Robust Statistics |
| |
| HU Yu-suo,CHEN Hui-yong,CHEN Zong-hai.Novel Strategy of Motion Detection and Object Tracking Based on Robust Statistics[J].Journal of System Simulation,2006,18(2):439-443. |
| |
| Authors: | HU Yu-suo CHEN Hui-yong CHEN Zong-hai |
| |
| Institution: | MOE-Mierosoft Key Laboratory of Multimedia Computing and Communication, University of Science and Technology of China, Hefei 230027, China; Department of Automation, University of Science and Technology of China, Hefei 230027, China |
| |
| Abstract: | A novel motion detection method based on robust statistics was proposed.It used global motion estimation and hypothesis test to detect the independently moving objects in the video sequence captured by a moving camera.To improve the accuracy of the detection algorithm,occlusion effect was compensated by bi-directional motion estimation.Based on it,a robust active contour model was proposed to track the contours of the moving objects.The model was solved using Level Set method.Experimental results on real-world data show that the proposed algorithm can detect and track the moving objects correctly and reliably. |
| |
| Keywords: | Level Set |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
