Improvement on optical flow based video deinterlacing by adopting flow vector and intensity reliabilities

  • Authors:
  • Yun-Jun Choi;Kyoung Won Lim;Jong Beom Ra

  • Affiliations:
  • Division of Electrical Engineering, School of Electrical Engineering & Computer Science, Korea Institute of Science and Technology, Korea;LG Electronics, Korea;Division of Electrical Engineering, School of Electrical Engineering & Computer Science, Korea Institute of Science and Technology, Korea

  • Venue:
  • ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

A recently introduced optical flow based deinterlacing algorithm showed a promising performance for the sequences with well estimated optical flows. However, estimated optical flows mostly include some errors, which cause significant artifacts. To reduce such artifacts, we propose an improved algorithm by considering flow vector reliability in terms of motion linearity, motion uniqueness, and consistent motion in a flat region. Moreover, to maximize the resolution of deinterlaced images, we propose intensity reliability which utilizes the field parity information. Experimental results show that the proposed algorithm noticeably improves the quality of deinterlaced images.