Increment adaptive correlation filter for visual tracking

Currently, the correlation filter is widely used in visual tracking because of its effectiveness and efficiency. To adapt the representation to changing target appearances, a linear interpolation is used to update tracking models according to a manually designed learning rate. However, The limitation of manually tricks make methods only apply to some special scenes because the threshold parameters are sensitive to different response maps in complex scenes. In this paper, to overcome this problem, an adaptive increment correlation filter based tracker is proposed. Different from traditional linear interpolation depending on a manual learning rate, the increment is learned by linear regression based on the history tracking model and the current training samples. Experimentally, we show that our algorithm can outperform state-of-the-art key point-based trackers.

• Publication year

  2020

• Venue

  International Symposium on Multispectral Image Processing and Pattern Recognition

• Publication date

  2020-02-14

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1117/12.2541744
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Context-Aware Correlation Filter Tracking

  2017cited by this paper
• Target Response Adaptation for Correlation Filter Tracking

  2016cited by this paper
• In Defense of Sparse Tracking: Circulant Sparse Tracker

  2016cited by this paper
• Structural Correlation Filter for Robust Visual Tracking

  2016cited by this paper
• Long-term correlation tracking

  2015cited by this paper
• Staple: Complementary Learners for Real-Time Tracking

  2015cited by this paper
• Object Tracking Benchmark

  2015cited by this paper
• Multi-template Scale-Adaptive Kernelized Correlation Filters

  2015cited by this paper
• Robust Object Tracking via Sparse Collaborative Appearance Model

  2014cited by this paper
• MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization

  2014cited by this paper
• A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration

  2014cited by this paper
• Accurate Scale Estimation for Robust Visual Tracking

  2014cited by this paper
• Tracking-Learning-Detection

  2012cited by this paper
• Exploiting the Circulant Structure of Tracking-by-Detection with Kernels

  2012cited by this paper
• Struck: Structured output tracking with kernels

  2011cited by this paper
• Robust Object Tracking with Online Multiple Instance Learning

  2011cited by this paper
• Visual object tracking using adaptive correlation filters

  2010cited by this paper
• On-Line Multi-view Forests for Tracking

  2010cited by this paper
• Rapid selection of reliable templates for visual tracking

  2010cited by this paper
• On-line Random Forests

  2009cited by this paper
• Semi-supervised On-Line Boosting for Robust Tracking

  2008cited by this paper
• Ensemble Tracking

  2005cited by this paper
• Histograms of oriented gradients for human detection

  2005cited by this paper
• The template update problem

  2004cited by this paper
• Kernel-Based Object Tracking

  2003cited by this paper
• Efficient Region Tracking With Parametric Models of Geometry and Illumination

  1998cited by this paper
• Ieee Transactions on Pattern Analysis and Machine Intelligence High-speed Tracking with Kernelized Correlation Filters

  year unknowncited by this paper

• No citing papers are available for this paper.