File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Conference Paper: Motion estimation method for blurred videos and application of deblurring with spatially varying blur kernels
  • Basic View
  • Metadata View
  • XML View
TitleMotion estimation method for blurred videos and application of deblurring with spatially varying blur kernels
 
AuthorsHe, XC1
Luo, T1
Yuk, SC1
Chow, KP1
Wong, KYK1
Chung, RHY2
 
KeywordsDeblurring
Motion Estimation
Spatially Varing Blur Kernels
 
Issue Date2010
 
CitationProceeding - 5Th International Conference On Computer Sciences And Convergence Information Technology, Iccit 2010, 2010, p. 355-359 [How to Cite?]
DOI: http://dx.doi.org/10.1109/ICCIT.2010.5711083
 
AbstractOptical flow methods, such as Lucas-Kanade and Horn-Schunck algorithms, are popular in motion estimation. However, they fall short on accuracy when they are applied to blurred videos. Some people utilize hybrid camera system to get a low resolution image to suppress the blurring effect so that more accurate optical flow for blurred high resolution image can be further derived, though in most of the practical environments it may not be feasible to deploy hybrid camera systems from cost perspective. In this paper, we propose a novel approach to estimate motion from a blurred video without the use of hybrid camera system, and to reduce motion blur by calculating its spatially varying blur kernels. Essentially, we first separate moving objects into small regions and use the corners of their boundaries as feature points, and then apply Hierarchical Block Matching Algorithm (HBMA) to track them between frames. Motions of non-corner pixels can therefore be estimated by interpolating the motion of these corner points, which further support the calculation of the spatially varying blur kernels for deblurring purpose. Experimental results demonstrate the effectiveness of proposed method.
 
DOIhttp://dx.doi.org/10.1109/ICCIT.2010.5711083
 
ReferencesReferences in Scopus
 
DC FieldValue
dc.contributor.authorHe, XC
 
dc.contributor.authorLuo, T
 
dc.contributor.authorYuk, SC
 
dc.contributor.authorChow, KP
 
dc.contributor.authorWong, KYK
 
dc.contributor.authorChung, RHY
 
dc.date.accessioned2012-06-26T06:32:15Z
 
dc.date.available2012-06-26T06:32:15Z
 
dc.date.issued2010
 
dc.description.abstractOptical flow methods, such as Lucas-Kanade and Horn-Schunck algorithms, are popular in motion estimation. However, they fall short on accuracy when they are applied to blurred videos. Some people utilize hybrid camera system to get a low resolution image to suppress the blurring effect so that more accurate optical flow for blurred high resolution image can be further derived, though in most of the practical environments it may not be feasible to deploy hybrid camera systems from cost perspective. In this paper, we propose a novel approach to estimate motion from a blurred video without the use of hybrid camera system, and to reduce motion blur by calculating its spatially varying blur kernels. Essentially, we first separate moving objects into small regions and use the corners of their boundaries as feature points, and then apply Hierarchical Block Matching Algorithm (HBMA) to track them between frames. Motions of non-corner pixels can therefore be estimated by interpolating the motion of these corner points, which further support the calculation of the spatially varying blur kernels for deblurring purpose. Experimental results demonstrate the effectiveness of proposed method.
 
dc.description.natureLink_to_subscribed_fulltext
 
dc.identifier.citationProceeding - 5Th International Conference On Computer Sciences And Convergence Information Technology, Iccit 2010, 2010, p. 355-359 [How to Cite?]
DOI: http://dx.doi.org/10.1109/ICCIT.2010.5711083
 
dc.identifier.doihttp://dx.doi.org/10.1109/ICCIT.2010.5711083
 
dc.identifier.epage359
 
dc.identifier.scopuseid_2-s2.0-79952689989
 
dc.identifier.spage355
 
dc.identifier.urihttp://hdl.handle.net/10722/151997
 
dc.languageeng
 
dc.relation.ispartofProceeding - 5th International Conference on Computer Sciences and Convergence Information Technology, ICCIT 2010
 
dc.relation.referencesReferences in Scopus
 
dc.subjectDeblurring
 
dc.subjectMotion Estimation
 
dc.subjectSpatially Varing Blur Kernels
 
dc.titleMotion estimation method for blurred videos and application of deblurring with spatially varying blur kernels
 
dc.typeConference_Paper
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>He, XC</contributor.author>
<contributor.author>Luo, T</contributor.author>
<contributor.author>Yuk, SC</contributor.author>
<contributor.author>Chow, KP</contributor.author>
<contributor.author>Wong, KYK</contributor.author>
<contributor.author>Chung, RHY</contributor.author>
<date.accessioned>2012-06-26T06:32:15Z</date.accessioned>
<date.available>2012-06-26T06:32:15Z</date.available>
<date.issued>2010</date.issued>
<identifier.citation>Proceeding - 5Th International Conference On Computer Sciences And Convergence Information Technology, Iccit 2010, 2010, p. 355-359</identifier.citation>
<identifier.uri>http://hdl.handle.net/10722/151997</identifier.uri>
<description.abstract>Optical flow methods, such as Lucas-Kanade and Horn-Schunck algorithms, are popular in motion estimation. However, they fall short on accuracy when they are applied to blurred videos. Some people utilize hybrid camera system to get a low resolution image to suppress the blurring effect so that more accurate optical flow for blurred high resolution image can be further derived, though in most of the practical environments it may not be feasible to deploy hybrid camera systems from cost perspective. In this paper, we propose a novel approach to estimate motion from a blurred video without the use of hybrid camera system, and to reduce motion blur by calculating its spatially varying blur kernels. Essentially, we first separate moving objects into small regions and use the corners of their boundaries as feature points, and then apply Hierarchical Block Matching Algorithm (HBMA) to track them between frames. Motions of non-corner pixels can therefore be estimated by interpolating the motion of these corner points, which further support the calculation of the spatially varying blur kernels for deblurring purpose. Experimental results demonstrate the effectiveness of proposed method.</description.abstract>
<language>eng</language>
<relation.ispartof>Proceeding - 5th International Conference on Computer Sciences and Convergence Information Technology, ICCIT 2010</relation.ispartof>
<subject>Deblurring</subject>
<subject>Motion Estimation</subject>
<subject>Spatially Varing Blur Kernels</subject>
<title>Motion estimation method for blurred videos and application of deblurring with spatially varying blur kernels</title>
<type>Conference_Paper</type>
<description.nature>Link_to_subscribed_fulltext</description.nature>
<identifier.doi>10.1109/ICCIT.2010.5711083</identifier.doi>
<identifier.scopus>eid_2-s2.0-79952689989</identifier.scopus>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-79952689989&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
<identifier.spage>355</identifier.spage>
<identifier.epage>359</identifier.epage>
</item>
Author Affiliations
  1. The University of Hong Kong
  2. Unit 107B