Learning affinities and dependencies for multi-target tracking using a CRF model

@article{Yang2011LearningAA,
  title={Learning affinities and dependencies for multi-target tracking using a CRF model},
  author={Bo Yang and Chang Huang and Ramakant Nevatia},
  journal={CVPR 2011},
  year={2011},
  pages={1233-1240}
}
We propose a learning-based Conditional Random Field (CRF) model for tracking multiple targets by progressively associating detection responses into long tracks. Tracking task is transformed into a data association problem, and most previous approaches developed heuristical parametric models or learning approaches for evaluating independent affinities between track fragments (tracklets). We argue that the independent assumption is not valid in many cases, and adopt a CRF model to consider both… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 92 CITATIONS, ESTIMATED 29% COVERAGE

FILTER CITATIONS BY YEAR

2010
2019

CITATION STATISTICS

  • 13 Highly Influenced Citations

  • Averaged 11 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Similar Papers

Loading similar papers…