Improved kernelized correlation filters tracking algorithm with adaptive learning factor

Mengxin Pei, Weixing Li, Zunjie Ke, Qi Gao

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

4 Citations (Scopus)

Abstract

Tracking with kernelized correlation filters is a new idea recently proposed which is different from traditional methods based on target features. This method achieves fast tracking speed, however, it is seriously compromised when the tracking target has large-scale changes and severe occlusion. An improved update model based on kernelized correlation filters is proposed in this paper to effectively overcome the above problems. An adaptive learning factor is defined with Peak-to-sidelobe ratio which estimates the correlation between different candidate images. It achieves adaptive online update of the tracking model. Experiments demonstrates that the presented algorithm can adjust the learning factor in real time according to different scenarios, which results increased success rate of tracking. With the adaptive learning factor, the presented algorithm shows advanced adaptability to partial occlusions, illumination, and target scale variations.

Original languageEnglish
Title of host publicationProceedings of the 35th Chinese Control Conference, CCC 2016
EditorsJie Chen, Qianchuan Zhao, Jie Chen
PublisherIEEE Computer Society
Pages4009-4013
Number of pages5
ISBN (Electronic)9789881563910
DOIs
Publication statusPublished - 26 Aug 2016
Event35th Chinese Control Conference, CCC 2016 - Chengdu, China
Duration: 27 Jul 201629 Jul 2016

Publication series

NameChinese Control Conference, CCC
Volume2016-August
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference35th Chinese Control Conference, CCC 2016
Country/TerritoryChina
CityChengdu
Period27/07/1629/07/16

Keywords

  • adaptive learning factor
  • kernelized correlation filters
  • target tracking

Fingerprint

Dive into the research topics of 'Improved kernelized correlation filters tracking algorithm with adaptive learning factor'. Together they form a unique fingerprint.

Cite this