Skip to main navigation Skip to search Skip to main content

Initialization-Insensitive Visual Tracking through Voting with Salient Local Features

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper we propose an object tracking method in case of inaccurate initializations. To track objects accurately in such situation, the proposed method uses "motion saliency" and "descriptor saliency" of local features and performs tracking based on generalized Hough transform (GHT). The proposed motion saliency of a local feature emphasizes features having distinctive motions, compared to the motions which are not from the target object. The descriptor saliency emphasizes features which are likely to be of the object in terms of its feature descriptors. Through these saliencies, the proposed method tries to "learn and find" the target object rather than looking for what was given at initialization, giving robust results even with inaccurate initializations. Also, our tracking result is obtained by combining the results of each local feature of the target and the surroundings with GHT voting, thus is robust against severe occlusions as well. The proposed method is compared against nine other methods, with nine image sequences, and hundred random initializations. The experimental results show that our method outperforms all other compared methods.
Original languageEnglish
Title of host publication2013 IEEE International Conference on Computer Vision
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages2912-2919
Number of pages8
ISBN (Print)978-1-4799-2840-8
DOIs
Publication statusPublished - 8 Dec 2013
Event2013 IEEE International Conference on Computer Vision - Sydney, NSW, Australia
Duration: 1 Dec 2013 → 8 Dec 2013

Conference

Conference2013 IEEE International Conference on Computer Vision
Period1/12/13 → 8/12/13

Keywords

  • Target tracking
  • Robustness
  • Feature extraction
  • Adaptation models
  • Optical sensors
  • Databases

Fingerprint

Dive into the research topics of 'Initialization-Insensitive Visual Tracking through Voting with Salient Local Features'. Together they form a unique fingerprint.

Cite this