본문 바로가기
  • Home

Online Multi-Object Tracking by Learning Discriminative Appearance with Fourier Transform and Partial Least Square Analysis

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2020, 25(2), pp.49-58
  • DOI : 10.9708/jksci.2020.25.02.049
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : January 14, 2020
  • Accepted : February 3, 2020
  • Published : February 28, 2020

Seong-Ho Lee 1 SEUNGHWAN BAE 1

1인천대학교

Accredited

ABSTRACT

In this study, we solve an online multi-object problem which finds object states (i.e. locations and sizes) while conserving their identifications in online-provided images and detections. We handle this problem based on a tracking-by-detection approach by linking (or associating) detections between frames. For more accurate online association, we propose novel online appearance learning with discrete fourier transform and partial least square analysis (PLS). We first transform each object image into a Fourier image in order to extract meaningful features on a frequency domain. We then learn PLS subspaces which can discriminate frequency features of different objects. In addition, we incorporate the proposed appearance learning into the recent confidence-based association method, and extensively compare our methods with the state-of-the-art methods on MOT benchmark challenge datasets.

Citation status

* References for papers published after 2022 are currently being built.

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