본문 바로가기
  • Home
Basic Search

Utilizing Context of Object Regions for Robust Visual Tracking

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2024, 29(2), pp.79-86
  • DOI : 10.9708/jksci.2024.29.02.079
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : January 26, 2024
  • Accepted : February 14, 2024
  • Published : February 29, 2024

Janghoon Choi 1

1경북대학교

Accredited

ABSTRACT

In this paper, a novel visual tracking method which can utilize the context of object regions is presented. Conventional methods have the inherent problem of treating all candidate regions independently, where the tracker could not successfully discriminate regions with similar appearances. This was due to lack of contextual modeling in a given scene, where all candidate object regions should be taken into consideration when choosing a single region. The goal of the proposed method is to encourage feature exchange between candidate regions to improve the discriminability between similar regions. It improves upon conventional methods that only consider a single region, and is implemented by employing the MLP-Mixer model for enhanced feature exchange between regions. By implementing channel-wise, inter-region interaction operation between candidate features, contextual information of regions can be embedded into the individual feature representations. To evaluate the performance of the proposed tracker, the large-scale LaSOT dataset is used, and the experimental results show a competitive AUC performance of 0.560 while running at a real-time speed of 65 fps.

Statistics

  • 95 Viewed
  • 45 Downloaded

Tools

Issue List

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.
Basic Search Advanced Search