基于特征点匹配技术的运动估计及补偿方法

Motion Estimation and Motion Compensation Based on Matching Technology of Feature Point

提出一种用于电子稳像技术的全局运动估计和补偿算法。通过特征点匹配,求其局部运动矢量;将其代入变换模型所得的线性方程组,求其全局运动矢量。用均值滤波的方法确定各帧的补偿量,并代入给定的变换模型对当前图像进行变换,实现对视频图像序列的稳定处理。为了减小特征点匹配计算的复杂性,加快匹配速度,还采用了多分辨率图像金字塔匹配策略。实验表明,使用该算法对于提高动态图像的稳定性有较好的效果。

An algorithm of global motion estimation and compensation applied to electric digital image stabilization was presented. The local motion vector of the block was determined by feature point matching. Global motion vector between the reference frame and the current frames is obtained by solution of a set of linear equations which came form a given motion model. The parameters to compensate the current image can be determined by average value filtering and have been applied to give motion model to stabilize the image stream. In order to reduce the computation complexity and speed matching a multi-resolution strategy was adopted. The experiments show that the algorithm has a better effect for improving dynamic image stabilization.