Robust Tracking for Motion Blur Based on Correlation Filter

Yu Bai, Tingfa Xu, Ruoling Yang, Xueyuan Sun, Yue Yu

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

1 Citation (Scopus)

Abstract

Correlation filter methods show good performance in robustness, accuracy and speed in visual tracking. In this paper, we propose a new algorithm based on Kernelized Correlation Filter (KCF) to effectively improve performance on motion blur. We adopt a simple and effective image deblurring method based on dark channel prior, combined with correlation filter to form a new Deblurring Correlation Filter (DECF) tracking algorithm. Extensive experimental results on OTB2015 show that our tracker demonstrates the excellent accuracy on tracking with motion blur.

Original languageEnglish
Title of host publicationProceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages309-312
Number of pages4
ISBN (Electronic)9781538681398
DOIs
Publication statusPublished - Apr 2019
Event2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019 - Fuzhou, Fujian, China
Duration: 26 Apr 201929 Apr 2019

Publication series

NameProceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019

Conference

Conference2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019
Country/TerritoryChina
CityFuzhou, Fujian
Period26/04/1929/04/19

Keywords

  • correlation filter
  • dark channel prior
  • motion blur
  • visual tracking

Fingerprint

Dive into the research topics of 'Robust Tracking for Motion Blur Based on Correlation Filter'. Together they form a unique fingerprint.

Cite this