UAV Target Tracking Algorithm Based on Kernel Correlation Filter

Jingkun Qu, Jinxiang Xu*

*Corresponding author for this work

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

Abstract

At present, there are still some problems in the tracking of ground targets by UAV, such as the poor tracking effect when the targets are moving rapidly, rotating and the target size is small. Therefore, this paper proposes an improved kernel correlation filtering algorithm. Firstly, the target is segmented adaptively according to the length-width ratio, and the maximum response is calculated by using the fusion feature, which is obtained by extracting the HOG feature and CN feature of each sub-block. Secondly, the position filter is used to locate the target, and the size filter estimates the size of the target. Finally, a re-detection mechanism is introduced to judge whether to update the filter based on the APCE value. The experimental results show that in the process of UAV target tracking, the improved algorithm can effectively reduce the influence of external interference on the tracking effect and improve the tracking effect.

Original languageEnglish
Title of host publicationProceedings of 2021 International Conference on Autonomous Unmanned Systems, ICAUS 2021
EditorsMeiping Wu, Yifeng Niu, Mancang Gu, Jin Cheng
PublisherSpringer Science and Business Media Deutschland GmbH
Pages1234-1243
Number of pages10
ISBN (Print)9789811694912
DOIs
Publication statusPublished - 2022
EventInternational Conference on Autonomous Unmanned Systems, ICAUS 2021 - Changsha, China
Duration: 24 Sept 202126 Sept 2021

Publication series

NameLecture Notes in Electrical Engineering
Volume861 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Autonomous Unmanned Systems, ICAUS 2021
Country/TerritoryChina
CityChangsha
Period24/09/2126/09/21

Keywords

  • Feature fusion
  • Kernel correlation filtering
  • Target block
  • Target tracking

Fingerprint

Dive into the research topics of 'UAV Target Tracking Algorithm Based on Kernel Correlation Filter'. Together they form a unique fingerprint.

Cite this