三维动态偏移场模型及其在视频跟踪技术中的应用  

3-D Dynamic Displacement Field Model and Its Application to Video Tracking Systems

作　　者：刘艳[1] 邹谋炎[2] 

机构地区：[1]中国科学院研究生院,北京100190 [2]中国科学院电子学研究所,北京100190

出　　处：《电子与信息学报》2008年第11期2784-2787,共4页Journal of Electronics & Information Technology

摘　　要：基于二维动态偏移场模型,该文提出了动态偏移场模型的三维描述形式,实现了对目标沿景深方向运动状态的描述,并为失真图像序列的动态偏移提供了由平面偏移估计到空间运动状态估计的渐进描述。在视频跟踪系统中,较之其他视频跟踪技术,基于三维偏移场模型理论,该文实现了跟踪视频序列的稳定化和对被跟踪目标运动状态的估计。Based on the 2-D dynamic displacement field model, the dynamic displacement model is extended from 2-D to 3-D. It realizes the description for the motion state estimation of the target in the depth direction of the sight field. It provides a gradually description process for distorted image sequence from estimating plane displacements to estimating spatial motion state. Compared to other video tracking techniques, based on the 3-D dynamic displacement field model, it has been implemented to stabilize the tracking sequence and estimate the target＇s motion state.

关 键 词：图像序列失真 三维动态偏移场模型 视频跟踪 运动状态估计 

分 类 号：TN911.73[电子电信—通信与信息系统]