精确运动估计的核回归修正梯度互相关算法  

Accurate motion estimation based on gradient cross-correlation algorithm with kernel regression refining

作　　者：余应淮[1] 谢仕义[1] 梅其祥[1] YU Yinghuai;XIE Shiyi;MEI Qixiang(College of Information, Guangdong Ocean University, Zhanjiang, Guangdong 524088, China)

机构地区：[1]广东海洋大学信息学院,广东湛江524088

出　　处：《计算机工程与应用》2017年第14期214-221,共8页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61272534);广东海洋大学创新强校工程项目(No.2015KQNCX056);湛江市科技计划项目(No.2015B01009)

摘　　要：为实现亚像素运动矢量的精确估计,探讨一种基于核回归修正的梯度互相关精确运动估计算法。引入优化滤波中心差分估计器计算图像梯度;基于矩阵相乘离散傅里叶变换方法快速计算上采样梯度互相关函数,以该函数的峰值坐标生成运动矢量的亚像素级初始估计值;在上采样梯度互相关曲面上,采用核回归方法对以初始估计值为中心的邻域进行拟合,并通过检测核回归拟合函数的峰值坐标获得初始估计的精确修正值,从而实现任意精度级别的精确运动估计。与相关文献的算法进行实验比较,在无噪声影响的情况下,所探讨算法的运动估计准确度提高了74%以上;而在噪声影响的情况下,运动估计的准确度则提高了68%以上。实验结果表明,所探讨算法不仅具备良好的抗噪性能,同时能够有效地提高运动估计的精确性。Concerning highly accurate sub-pixel motion estimation,an improved algorithm based on gradient crosscorrelationwith kernel regression refining is proposed.Firstly,the spatial gradient of the image is generated using an optimalfilter.Secondly,an upsampled gradient cross-correlation is computed efficiently by means of matrix-multiply discreteFourier transform,and the initial estimation of motion vector with sub-pixel accuracy procured by the peak of it.Finally,akernel regression function is fit to the upsampled gradient cross-correlation values in a neighborhood of initial estimation,then refines the initial estimation with the location of peak found in the kernel regression fitting function,so as to obtainaccurate estimation at arbitrary-precision.In the comparison experiments with some state-of-the-art algorithms,the accuracyof motion estimation of proposed scheme increases by more than74%in the case of noise-free;while under the noise condition,the accuracy is improved by more than68%.Experimental results show that the proposed algorithm can not onlyachieve good robustness to the influence of noise,but can also improve the accuracy of motion estimation significantly.

关 键 词：运动估计 梯度互相关 优化滤波器 上采样 矩阵相乘 核回归 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]