ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1504.06103
60
38
v1v2 (latest)

Online Adaptive Hidden Markov Model for Multi-Tracker Fusion

23 April 2015
Tomás Vojír
Jirí Matas
Jana Noskova
    VOT
ArXiv (abs)PDFHTML
Abstract

In this paper, we propose a novel method for visual tracking called HMMTxD. The method fuses information from complementary trackers and a detector by utilizing a hidden Markov model whose latent states correspond to a binary vector expressing the failure of individual trackers. The Markov model is trained in an unsupervised way, relying on an online learned detector to provide a source of tracker-independent information for a modified Baum-Welch algorithm that updates the model w.r.t. the partially annotated data. We show the effectiveness of this approach on combination of two and three tracking methods. The performance of HMMTxD is evaluated on two standard benchmarks (CVPR2013 and VOT) and on a rich collection of 77 publicly available sequences. The HMMTxD outperforms the state-of-the-art, often significantly, on all datasets in almost all criteria.

View on arXiv
Comments on this paper