改进的CLG变分光流场估计方法

Improved method for variational optical flow field estimation based on CLG

光流运动估计是计算机视觉领域的一个重要的研究领域,为了抑制噪声对光流场估计的影响,并实现大位移光流场求解,建立了基于全局与局部相结合的CLG-TV变分光流估计模型,并提出求解方法。将LK局部光流算法融合到TV-L1模型中,并利用各项异性扩散和双边滤波技术,扩展后模型在保持TV-L1模型优势的基础上,具有更加鲁棒的抗噪性能,且能有效解决大位移问题;在求解过程中,利用结构纹理分解方法和由粗到精金字塔方法,提高光流计算的精度。实验结果表明:本算法误差AAE和AEPE均有所减小,该算法在精度提高的同时加快了收敛速度;进一步,通过对实际大位移图像序列求解,验证了算法能有效区分动态目标和静态背景的能力,并且能较好反映物体的运动信息。本文提出的CLG-TV模型能够提高光流估计精度,并能有效解决光流计算的大位移问题。

Optical flow motion estimation is an important area of computer vision research. To suppress the impact on optical flow estimation caused by noise and solve the large displacement optical flow, a CLG-TV variational optical flow estimation model based on CLG（Combined Local and Global） method is established. CLG method is utilized to integrate TV-L1 model with LK algorithm, which is the local optical flow estimation method, and anisotropic diffusion and bilateral filtering technology are adopted in CLG-TV model. On the basis of the TV-L1 model advantages, this model has high robustness to noise and ability to solve large displacement problem. And structure and texture decomposition method is integrated with coarse-to-fine approach during the solution process to improve the accuracy of optical flow computation. The experimental results show that the AAE error and the AEPE error are decreased with this proposed algorithm. It is proved that the accuracy is improved and the convergence rate is accelerated. Meanwhile, through practical large displacement image sequence verification, dynamic objects and static background can be effectively distinguished and objects movement information can better reflected. The proposed CLG-TV model can improve the optical flow estimation accuracy and solve the large displacement problem of optical flow calculation effectively.