arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1603.02253cs.CV
收藏

基于运动通道的鲁棒光流模糊算法

Blur Robust Optical Flow using Motion Channel

University College London(伦敦大学学院);University of Bath(巴斯大学);Imperial College London(帝国理工学院);Xiamen University of Technology(厦门理工学院)

Wenbin Li, Yang Chen, JeeHang Lee, Gang Ren, Darren Cosker

摘要:

给定具有相机抖动和其他运动模糊的真实世界视频序列,难以估计光流。在本文中,我们首先研究模糊参数化的视频镜头使用近线性运动元素。然后,我们将商用3D姿态传感器与RGB相机组合,以便将感兴趣的视频片段与相机运动一起拍摄。我们说明,这个额外的相机运动/轨迹通道可以嵌入到一个混合框架,通过交错的迭代盲反卷积和翘曲的光流计划。我们的方法在其他三个最先进的基线内产生了更高的精度,给出了我们提出的地面真实模糊序列;以及我们的成像系统拍摄的其他几个真实世界序列。

英文摘要:

It is hard to estimate optical flow given a realworld video sequence with camera shake and other motion blur. In this paper, we first investigate the blur parameterization for video footage using near linear motion elements. we then combine a commercial 3D pose sensor with an RGB camera, in order to film video footage of interest together with the camera motion. We illustrates that this additional camera motion/trajectory channel can be embedded into a hybrid framework by interleaving an iterative blind deconvolution and warping based optical flow scheme. Our method yields improved accuracy within three other state-of-the-art baselines given our proposed ground truth blurry sequences; and several other realworld sequences filmed by our imaging system.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑