Structural correlation filters combined with a Gaussian particle filter for hierarchical visual tracking

Manna Dai, Gao Xiao, Shuying Cheng, Dadong Wang, Xiangjian He

Research output: Journal PublicationArticlepeer-review

5 Citations (Scopus)

Abstract

Visual tracking is a key problem for many computer vision applications such as human-computer interaction, intelligent medical diagnosis, navigation and traffic control management. Most of the existing tracking methods are mainly based on correlation filters. However, boundary effect, scale estimation and template updating have not been fully resolved. Herein, this paper presents a new hierarchical tracking method combining structural correlation filters with a Gaussian Particle Filter (GPF), named KCF-GPF. Weak KCF classifiers are constructed via a Lukas-Kanade (LK) method and the preliminary target location is presented as a weighted sum of these classifiers. Specially, a facile weight strategy is implemented to estimate the reliability of each weak classifier. On the basis of the preliminary target location, the GPF using features from a Convolutional Neural Network (CNN) is employed to predict the location and scale of a target. Extensive experiments with the OTB-2013 and the OTB-2015 databases demonstrate that the proposed algorithm performs favourably against state-of-the-art trackers.

Original languageEnglish
Pages (from-to)235-246
Number of pages12
JournalNeurocomputing
Volume398
DOIs
Publication statusPublished - 20 Jul 2020
Externally publishedYes

Keywords

  • Convolutional Neural Network (CNN)
  • Gaussian Particle Filter (GPF)
  • Lukas-Kanade (LK)
  • Reliability estimation
  • Structural correlation filter

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Structural correlation filters combined with a Gaussian particle filter for hierarchical visual tracking'. Together they form a unique fingerprint.

Cite this