光流
计算机科学
计算机视觉
人工智能
计算
平滑的
像素
流量(数学)
正规化(语言学)
算法
运动估计
数学
图像(数学)
几何学
作者
Jun Chen,Hui DuanStudent Member,Yuanxin SongStudent Member,Zemin Cai,Guangguang Yang
标识
DOI:10.1109/tmm.2022.3207583
摘要
Optical flow computation for video under the dynamic illumination is a challenging issue in video multimedia applications. In this paper, we solve this issue by introducing an illumination-invariant framework for variational optical flow estimation. It consists of an illumination-invariance model that handles complex illumination changes and a data enhancement model that guarantees highly accurate optical flow estimation. In this framework, we design a log-correlation descriptor for the data term, which handles complex illumination changes by eliminating the common parameters shared by the neighboring pixels in the corresponding illumination change model while improving the accuracy of optical flow estimation by enhancing the discriminability of the data term matching. We also introduce a novel optical flow model with $L_{0}$ norm regularization, which reconstructs optical flow field by a sparse flow gradient counting scheme. Different from other edge-preserving regularizers, it does not depend on local motion features, but locates important flow edges globally. Therefore, it will not cause edge blurriness due to avoiding local filtering or average operation. It is particularly effective for enhancing major flow edges while eliminating a manageable degree of low-amplitude motion structures to control smoothing and reduce oversegmentation artifacts. Even small-scale motion structures with high contrast can be preserved remarkably well. The experimental results show our method significantly outperforms previous illumination-robust optical flow methods in handling complex illumination changes, and achieves competitive evaluation results on the challenging MPI-Sintel and Kitti datasets.
科研通智能强力驱动
Strongly Powered by AbleSci AI