全局运动估计的阈值可变双迭代法  

A Double-Iteration Algorithm with Variable Thresholdfor Global Motion Estimation

作　　者：陈韩锋[1] 戚飞虎[1] 

机构地区：[1]上海交通大学计算机科学与工程系,上海200030

出　　处：《上海交通大学学报》2004年第1期1-4,共4页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金资助项目(60072029)

摘　　要：提出了一种全局运动区域检测与全局运动模型参数估计的阈值可变双迭代法.该方法包含两个迭代过程:1迭代最小二乘法进行参数的估计,迭代过程中用可变的百分比阈值去除局部运动点的干扰:2检测完整的全局运动区域并得到最后的模型参数.阈值可变双迭代法对不同视频的适应能力较强,得到的全局运动区域更完整,模型参数的估计更稳定.实验结果验证了该方法的可行性和优越性.A double-iteration algorithm with variable threshold was proposed to detect global motion regions (GMR) and estimate parameters of the global motion model (PGMM). The proposed algorithm comprises two iterative processes. Firstly, the PGMM is estimated with an iterative least squares algorithm. A variable threshold is introduced to eliminate the disturbance of local motion. Then, the GMR is detected and the final PGMM is calculated on the GMR in the second iterative process. The proposed algorithm is adaptive to various sequences and accurate in getting the GMR and PGMM.The experiments show the validity and advances of the algorithm.

关 键 词：全局运动估计 摄像机运动模型 最小二乘法 可变阈值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]