What are we tracking: A unified approach of tracking and recognition

Jialue Fan*, Xiaohui Shen, Ying Wu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

24 Scopus citations

Abstract

Tracking is essentially a matching problem. While traditional tracking methods mostly focus on low-level image correspondences between frames, we argue that high-level semantic correspondences are indispensable to make tracking more reliable. Based on that, a unified approach of low-level object tracking and high-level recognition is proposed for single object tracking, in which the target category is actively recognized during tracking. High-level offline models corresponding to the recognized category are then adaptively selected and combined with low-level online tracking models so as to achieve better tracking performance. Extensive experimental results show that our approach outperforms state-of-the-art online models in many challenging tracking scenarios such as drastic view change, scale change, background clutter, and morphable objects.

Original languageEnglish (US)
Article number6302190
Pages (from-to)549-560
Number of pages12
JournalIEEE Transactions on Image Processing
Volume22
Issue number2
DOIs
StatePublished - Jan 21 2013

Keywords

  • Object recognition
  • video analysis
  • visual tracking

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'What are we tracking: A unified approach of tracking and recognition'. Together they form a unique fingerprint.

Cite this