Visual Tracking via Nonnegative Multiple Coding

Fanghui Liu, Chen Gong, Tao Zhou, Keren Fu, Xiangjian He, Jie Yang

Research output: Journal PublicationArticlepeer-review

16 Citations (Scopus)


It has been extensively observed that an accurate appearance model is critical to achieving satisfactory performance for robust object tracking. Most existing top-ranked methods rely on linear representation over a single dictionary, which brings about improper understanding on the target appearance. To address this problem, in this paper, we propose a novel appearance model named as "nonnegative multiple coding" (NMC) to accurately represent a target. First, a series of local dictionaries are created with different predefined numbers of nearest neighbors, and then the contributions of these dictionaries are automatically learned. As a result, this ensemble of dictionaries can comprehensively exploit the appearance information carried by all the constituted dictionaries. Second, the existing methods explicitly impose the nonnegative constraint to coefficient vectors, but in the proposed model, we directly deploy an efficient l2 norm regularization to achieve the similar nonnegative purpose with theoretical guarantees. Moreover, an efficient occlusion detection scheme is designed to alleviate tracking drifts, which investigates whether negative templates are selected to represent the severely occluded target. Experimental results on two benchmarks demonstrate that our NMC tracker are able to achieve superior performance to state-of-the-art methods.

Original languageEnglish
Article number7934396
Pages (from-to)2680-2691
Number of pages12
JournalIEEE Transactions on Multimedia
Issue number12
Publication statusPublished - Dec 2017
Externally publishedYes


  • Approximated locality-constrained linear coding
  • nonnegative constraint
  • occlusion detection
  • visual tracking

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Visual Tracking via Nonnegative Multiple Coding'. Together they form a unique fingerprint.

Cite this