A Biologically Inspired Appearance Model for Robust Visual Tracking

Shengping Zhang*, Xiangyuan LAN, Hongxun Yao, Huiyu Zhou, Dacheng Tao, Xuelong Li

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

66 Citations (Scopus)

Abstract

In this paper, we propose a biologically inspired appearance model for robust visual tracking. Motivated in part by the success of the hierarchical organization of the primary visual cortex (area V1), we establish an architecture consisting of five layers: Whitening, rectification, normalization, coding, and pooling. The first three layers stem from the models developed for object recognition. In this paper, our attention focuses on the coding and pooling layers. In particular, we use a discriminative sparse coding method in the coding layer along with spatial pyramid representation in the pooling layer, which makes it easier to distinguish the target to be tracked from its background in the presence of appearance variations. An extensive experimental study shows that the proposed method has higher tracking accuracy than several state-of-the-art trackers.

Original languageEnglish
Article number7516592
Pages (from-to)2357-2370
Number of pages14
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume28
Issue number10
DOIs
Publication statusPublished - Oct 2017

Scopus Subject Areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

User-Defined Keywords

  • Appearance modeling
  • biologically inspiration
  • sparse coding
  • visual tracking

Fingerprint

Dive into the research topics of 'A Biologically Inspired Appearance Model for Robust Visual Tracking'. Together they form a unique fingerprint.

Cite this