• Home
  • Search
  • Long‐time target tracking algorithm based on re‐detection multi‐feature fusion
  • Cite Icon1
  • https://doi.org/10.1049/csy2.12042Copy DOI Icon

Long‐time target tracking algorithm based on re‐detection multi‐feature fusion

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Abstract This paper considers the problem of long‐term target tracking in complex scenes when tracking failures are unavoidable due to illumination change, target deformation, scale change, motion blur, and other factors. More specifically, a target tracking algorithm, called re‐detection multi‐feature fusion, is proposed based on the fusion of scale‐adaptive kernel correlation filtering and re‐detection. The target tracking algorithm trains three kernel correlation filters based on the histogram of oriented gradients, colour name, and local binary pattern features and then obtains the fusion weight of response graphs corresponding to different features based on average peak correlation energy criterion and uses weighted average to complete the position estimation of the tracked target. In order to deal with the problem that the target is occluded and disappears in the tracking process, a random fern classifier is trained to perform re‐detection when the target is occluded. After comparing the OTB‐50 target tracking dataset, the experimental results show that the proposed tracker can track the target well in the occlusion attribute video sequence in the OTB‐100 test dataset and has a certain improvement in tracking accuracy and success rate compared with the traditional correlation filter tracker.

Similar Papers
  • Conference Article
  • Citations1

A research of target tracking algorithm based on deep learning and kernel correlation filter

  • Jul 18, 2022
  • Shengtao Sun +4
  • PDF
  • Research Article
  • Citations2

Scale Adaptive Kernel Correlation Filter Tracking Algorithm Combined with Learning Rate Adjustment

  • Jan 01, 2018
  • MATEC Web of Conferences
  • Di Wu +1
  • Book Chapter

An Adaptive Multi-scale Tracking Method Based on Kernelized Correlation Filter

  • Jan 01, 2018
  • Qiling Xu +1
  • Conference Article
  • Citations1

Target tracking algorithm based on improved kernel correlation filtering

  • Oct 22, 2021
  • Haode Shi +5
  • Conference Article
  • Citations4

Target tracking algorithm based on image matching and improved kernel correlation filter

  • Sep 23, 2021
  • Weimin Hou +4
  • PDF
  • Research Article
  • Citations16

Correlation Filter With Motion Detection for Robust Tracking of Shape-Deformed Targets

  • Jan 01, 2020
  • IEEE Access
  • Chengyuan Liu +4
  • Conference Article
  • Citations1

Adaptive Correlation Filtering Algorithm for Video Target Tracking based on Multi Feature Fusion

  • Jun 01, 2019
  • Yifei Fan +1
  • PDF
  • Research Article
  • Citations1

Anti-Similar Visual Target Tracking Algorithm Based on Filter Peak Guidance and Fusion Network

  • Jul 07, 2023
  • Electronics
  • Jing Wang +4
  • Conference Article

TRIT: A Robust Tracker Based on Triplet Network

  • Nov 23, 2019
  • Peng Zou +1
  • Conference Article
  • Citations3

Using KCF and face recognition for outdoor target tracking UAV

  • May 06, 2019
  • Lu Chen +7
  • PDF
  • Research Article
  • Citations8

Long-Term Target Tracking of UAVs Based on Kernelized Correlation Filter

  • Nov 24, 2021
  • Mathematics
  • Junqiang Yang +2
  • PDF
  • Research Article
  • Citations13

Deep Learning-Based Ground Target Detection and Tracking for Aerial Photography from UAVs

  • Sep 11, 2021
  • Applied Sciences
  • Kaipeng Wang +2
  • Conference Article
  • Citations1

Interacting with target tracking algorithms in a gaze-enhanced motion video analysis system

  • May 13, 2016
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Jutta Hild +4
  • Conference Article
  • Citations2

Research on target detection and tracking method applied to intelligent monitoring system

  • Jun 28, 2021
  • Shaona Wang +3
  • Research Article
  • Citations1

A Long-term Tracking Model Based on Tracking Failure Detection Strategy and Weighted Random Forest

  • Dec 21, 2016
  • DEStech Transactions on Engineering and Technology Research
  • Tao Zhu +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.