Adaptive large window correlation for optical flow estimation with discrete optimization

作者：

Highlights：

• A method based on using large correlation windows with adaptive support-weights

• Three new weighting constraints from image gradient, color statistics and occlusion

• Contributes to suppress the effect of cluttered background in the windows

• Elevates the quality of estimations especially on object boundaries

摘要

•A method based on using large correlation windows with adaptive support-weights•Three new weighting constraints from image gradient, color statistics and occlusion•Contributes to suppress the effect of cluttered background in the windows•Elevates the quality of estimations especially on object boundaries

论文关键词：Window correlation,Optical flow,Data cost,Discrete optimization

论文评审过程：Received 8 November 2012, Revised 3 April 2013, Accepted 19 June 2013, Available online 29 June 2013.

论文官网地址：https://doi.org/10.1016/j.imavis.2013.06.009