计算机工程与应用 ›› 2017, Vol. 53 ›› Issue (14): 214-221.DOI: 10.3778/j.issn.1002-8331.1601-0313

• 图形图像处理 • 上一篇    下一篇

精确运动估计的核回归修正梯度互相关算法

余应淮,谢仕义,梅其祥   

  1. 广东海洋大学 信息学院,广东 湛江 524088
  • 出版日期:2017-07-15 发布日期:2017-08-01

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

YU Yinghuai, XIE Shiyi, MEI Qixiang   

  1. College of Information, Guangdong Ocean University, Zhanjiang, Guangdong 524088, China
  • Online:2017-07-15 Published:2017-08-01

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。

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

Abstract: Concerning highly accurate sub-pixel motion estimation, an improved algorithm based on gradient cross-correlation with kernel regression refining is proposed. Firstly, the spatial gradient of the image is generated using an optimal filter. Secondly, an upsampled gradient cross-correlation is computed efficiently by means of matrix-multiply discrete Fourier transform, and the initial estimation of motion vector with sub-pixel accuracy procured by the peak of it. Finally, a kernel 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 obtain accurate estimation at arbitrary-precision. In the comparison experiments with some state-of-the-art algorithms, the accuracy of motion estimation of proposed scheme increases by more than 74% in the case of noise-free; while under the noise condition, the accuracy is improved by more than 68%. Experimental results show that the proposed algorithm can not only achieve good robustness to the influence of noise, but can also improve the accuracy of motion estimation significantly.

Key words: motion estimation, gradient cross-correlation, optimal filter, upsampling, matrix-multiplication, kernel regression