Robust Real-Time Object Tracking System for Human-Following Quadruped Robot

Hailun Zhang, Xuemei Ren*

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

Quadruped robot needs a real-time robust object tracking algorithm and an accurate and stable servo controller for human following task. The object tracking algorithm in this paper used the Kalman filter to generate the pre-sampling area for Kernel Correlation Filter (KCF) according to the motion state, and the object detection is used to periodically evaluate and update the tracking box of KCF according to the scale change rate and the center offset error, so as to realize the scale adaptation and prevent missed detection. Based on the visual information provided by the target tracking algorithm, the kinematics of the target following task are modeled, and the kinematic controller satisfying the Lyapunov stability is designed based on backstepping. Through simulation experiments, the effectiveness and stability of the target tracking system proposed in this paper are verified.

Original languageEnglish
Title of host publicationProceedings of 2022 Chinese Intelligent Systems Conference - Volume I
EditorsYingmin Jia, Weicun Zhang, Yongling Fu, Shoujun Zhao
PublisherSpringer Science and Business Media Deutschland GmbH
Pages388-397
Number of pages10
ISBN (Print)9789811962028
DOIs
Publication statusPublished - 2022
Event18th Chinese Intelligent Systems Conference, CISC 2022 - Beijing, China
Duration: 15 Oct 202216 Oct 2022

Publication series

NameLecture Notes in Electrical Engineering
Volume950 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference18th Chinese Intelligent Systems Conference, CISC 2022
Country/TerritoryChina
CityBeijing
Period15/10/2216/10/22

Keywords

  • Backstepping
  • Kalman filter
  • Kernel correlation filter
  • Lyapunov stability
  • Object tracking

Fingerprint

Dive into the research topics of 'Robust Real-Time Object Tracking System for Human-Following Quadruped Robot'. Together they form a unique fingerprint.

Cite this