A Novel Performance Evaluation Methodology for Single-Target Trackers

@article{Kristan2016ANP,
  title={A Novel Performance Evaluation Methodology for Single-Target Trackers},
  author={Matej Kristan and Juan E. Sala Matas and Ale{\vs} Leonardis and Tom{\'a}s Voj{\'i}r and Roman P. Pflugfelder and Gustavo Fern{\'a}ndez and Georg Nebehay and Fatih Murat Porikli and Luka Cehovin},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2016},
  volume={38},
  pages={2137-2155}
}
  • Matej Kristan, Juan E. Sala Matas, +6 authors Luka Cehovin
  • Published 2016
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • This paper addresses the problem of single-target tracker performance evaluation. We consider the performance measures, the dataset and the evaluation system to be the most important components of tracker evaluation and propose requirements for each of them. The requirements are the basis of a new evaluation methodology that aims at a simple and easily interpretable tracker comparison. The ranking-based methodology addresses tracker equivalence in terms of statistical significance and practical… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 307 CITATIONS, ESTIMATED 76% COVERAGE

    A quantitative attribute-based benchmark methodology for single-target visual tracking

    The Sixth Visual Object Tracking VOT2018 Challenge Results

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS

    The Visual Object Tracking VOT 2017 challenge results

    VIEW 9 EXCERPTS
    CITES BACKGROUND & METHODS

    The Visual Object Tracking VOT2017 Challenge Results

    VIEW 17 EXCERPTS
    CITES METHODS & BACKGROUND

    The Visual Object Tracking VOT 2016 Challenge Results

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS

    The Visual Object Tracking VOT2016 Challenge Results

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS

    The Visual Object Tracking VOT 2015 Challenge Results

    VIEW 7 EXCERPTS
    CITES METHODS & BACKGROUND

    FILTER CITATIONS BY YEAR

    2014
    2020

    CITATION STATISTICS

    • 35 Highly Influenced Citations

    • Averaged 73 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 100 REFERENCES

    A Protocol for Evaluating Video Trackers Under Real-World Conditions

    Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics

    VIEW 1 EXCERPT

    Adaptive Appearance Modeling for Video Tracking: Survey and Evaluation

    VIEW 2 EXCERPTS

    The Visual Object Tracking VOT2013 Challenge Results

    VIEW 1 EXCERPT

    Adaptive Online Performance Evaluation of Video Trackers

    VIEW 1 EXCERPT

    Visual Tracking: An Experimental Survey

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    The Visual Object Tracking VOT2015 Challenge Results

    Visual Object Tracking Performance Measures Revisited