Weighted linear motion deblurring with blur kernel estimation using consecutive frames

Woo Jin Jeong, Jin Wook Park, Dong Seok Lee, Wonju Choi, Young Shik Moon

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

We propose an efficient algorithm for motion deblurring with kernel estimation using consecutive images. First we estimate motion vectors between consecutive images using optical flow and RANSAC. Then we calculate the weights of motion vectors. The proposed method is similar to Ben-Ezra's method. The main difference is that we use a single camera for estimating a blur kernel and capturing a blurred image. Experimental results have shown that the proposed method produces better deblurred images with less artifacts.

Original languageEnglish
Title of host publicationISCE 2014 - 18th IEEE International Symposium on Consumer Electronics
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479945924
DOIs
StatePublished - 2014
Event18th IEEE International Symposium on Consumer Electronics, ISCE 2014 - Jeju, Korea, Republic of
Duration: 22 Jun 201425 Jun 2014

Publication series

NameProceedings of the International Symposium on Consumer Electronics, ISCE

Conference

Conference18th IEEE International Symposium on Consumer Electronics, ISCE 2014
Country/TerritoryKorea, Republic of
CityJeju
Period22/06/1425/06/14

Keywords

  • consecutive frames
  • deblurring
  • kernel estimation
  • linear motion
  • video deblurring

Fingerprint

Dive into the research topics of 'Weighted linear motion deblurring with blur kernel estimation using consecutive frames'. Together they form a unique fingerprint.

Cite this