Optical flow estimation with adaptive convolution kernel prior on discrete framework
Optical flow estimation with adaptive convolution kernel prior on discrete framework
复制标题
DOI：
10.1109/cvpr.2010.5539953
复制
发表时间：
2010-06
期刊：
影响因子：
--
通讯作者：
Kyong Joon Lee;Dongjin Kwon;I. Yun;Sang Uk Lee
中科院分区：
文献类型：
--
作者：
Kyong Joon Lee;Dongjin Kwon;I. Yun;Sang Uk Lee
提出了一种新的离散磁流变函数框架光流估计能量模型。利用扩散张量正则化器对现有模型进行离散模拟，并采用变分方法进行优化。受正则化过程作为卷积核滤波这一事实的启发，我们将原始流和过滤后的流之间的差异表述为平滑先验。然后，离散框架使我们能够使用鲁棒惩罚器，而不涉及能量函数的凸性和可微性。此外，我们提出了一种新的基于双边滤波器的核设计，根据局部统计量自适应控制强度方差。该算法同时解决了难以通过参数调优实现的过分割和过平滑问题。针对具有大型标签集的复杂图结构，本文还提出了一种有效地将内存需求和计算时间降低到可容忍状态的策略。实验结果表明，该方法在包括大位移和纹理区域在内的各种数据集上取得了令人满意的结果。
We present a new energy model for optical flow estimation on discrete MRF framework. The proposed model yields discrete analog to the prevailing model with diffusion tensor-based regularizer, which has been optimized by variational approach. Inspired from the fact that the regularization process works as a convolution kernel filtering, we formulate the difference between original flow and filtered flow as a smoothness prior. Then the discrete framework enables us to employ a robust penalizer less concerning convexity and differentiability of the energy function. In addition, we provide a new kernel design based on the bilateral filter, adaptively controlling intensity variance according to the local statistics. The proposed kernel simultaneously addresses over-segmentation and over-smoothing problems, which is hard to achieve by tuning parameters. Involving a complex graph structure with large label sets, this work also presents a strategy to efficiently reduce memory requirement and computational time to a tolerable state. Experimental result shows the proposed method yields plausible results on the various data sets including large displacement and textured region.