Selection of Discriminative Tracking Features

@inproceedings{Collins2005SelectionOD,
  title={Selection of Discriminative Tracking Features},
  author={Robert T. Collins and Yanxi Liu and Marius Leordeanu},
  year={2005}
}
This paper presents an online feature selection mechanism for evaluating multiple features while tracking and adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that best discriminate between object and background are also best for tracking the object. Given a set of seed features, we compute log likelihood ratios of class conditional sample densities from object and background to form a new set of candidate features tailored to the local… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 97 CITATIONS, ESTIMATED 86% COVERAGE

Sparse Representation Tracking with Auxiliary Adaptive Appearance Models

VIEW 12 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Fragment-based Visual Tracking with Multiple Representations

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Context specific descriptors for tracking deforming tissue

  • Medical Image Analysis
  • 2012
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Dynamic Template Tracking and Recognition

  • International Journal of Computer Vision
  • 2012
VIEW 8 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

KL based data fusion for target tracking

  • Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)
  • 2012
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Margin based likelihood map fusion for target tracking

  • 2012 IEEE International Geoscience and Remote Sensing Symposium
  • 2012
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Automatic initialization and tracking using attentional mechanisms

  • CVPR 2011 WORKSHOPS
  • 2011
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

MEAN-shift tracking algorithm with weight fusion strategy

  • 2011 18th IEEE International Conference on Image Processing
  • 2011
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Robust Contour Tracking by Combining Region and Boundary Information

  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2011
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Closed-Loop Adaptation for Robust Tracking

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2005
2018

CITATION STATISTICS

  • 28 Highly Influenced Citations

  • Averaged 1 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 32 REFERENCES

Neural Networks for Pattern Recognition

C. Bishop
  • 1997
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Adaptive color space switching for face tracking in multi-colored lighting environments

  • Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition
  • 2002
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Active Appearance Models Revisited

  • International Journal of Computer Vision
  • 2004
VIEW 1 EXCERPT

A quantified study of facial asymmetry in 3D faces

  • 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)
  • 2003
VIEW 1 EXCERPT

Kernel-Based Object Tracking

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 2003
VIEW 1 EXCERPT

Probabilistic tracking in joint feature-spatial spaces

  • 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
VIEW 1 EXCERPT