一种基于检测块动态选择的稳像算法

A Dynamic Detection Blocks Selection-based Image Stabilization Algorithm

针对包含运动物体视频序列的稳像问题,提出了一种基于运动目标检测的数字稳像算法.该算法运用估计的全局运动参数补偿帧间全局运动,得到运动补偿前帧和当前帧的差值图像,并将差值图像分割成一系列的前景块和背景块,仅跟踪背景块来估计下一轮的全局运动参数.仿真结果表明,提出的稳像算法不仅计算复杂度低,而且估计的全局变换参数具有相当高的帧间变换保真度,可以用于占据半个像面的动目标的视频序列.

A moving object dedection-based image sabilization algorithm was propoed for addressesing the moving object problem of image sabilization.In the algorithm,the estimate global motion paramaters were used to compensate the inter-frame global motion,and the difference image between the motion compensated previous and current frames was obtained.Then,the difference image was divided into a series of forground and background blocks.And the global motion paramaters in the next run were estimated only by tracking the background blocks.Simulation results show that the proposedalgorithm has low computatiomal complexity,and achives quite high interframe transformation fidelity,which is suitable for stabilizing video clips with large moving objects.