A Novel Performance Evaluation Methodology for Single-Target Trackers

M. Kristan, J. Matas, A. Leonardis, T. Vojir, R. Pflugfelder, G. Fernandez, Georg Nebehay, F. Porikli and L. Cehovin

Abstract

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 differences. A fully-annotated dataset with per-frame annotations with several visual attributes is introduced. The diversity of its visual properties is maximized in a novel way by clustering a large number of videos according to their visual attributes. This makes it the most sophistically constructed and annotated dataset to date. A multi-platform evaluation system allowing easy integration of third-party trackers is presented as well. The proposed evaluation methodology was tested on the VOT2014 challenge on the new dataset and 38 trackers, making it the largest benchmark to date. Most of the tested trackers are indeed state-of-the-art since they outperform the standard baselines, resulting in a highly-challenging benchmark. An exhaustive analysis of the dataset from the perspective of tracking difficulty is carried out. To facilitate tracker comparison a new performance visualization technique is proposed.

Published In

Transactions on Pattern Analysis and Machine Intelligence, 2016.
Download the PDF PDF logo

Code

Download the code from our GitHub repository.GitHub logo

Project Page

More information is available at the Project page.

BibTex

@article{Kristan2016PAMI,
    author = {Kristan, Matej and Matas, Jiri and Leonardis, Ales and Vojir, Tomas and Pflugfelder, Roman and Fernandez, Gustavo and Nebehay, Georg and Porikli, Fatih and Cehovin, Luka},
    doi = {10.1109/tpami.2016.2516982},
    issn = {0162-8828},
    journal = {Pattern Analysis and Machine Intelligence},
    number = {11},
    pages = {2137--2155},
    publisher = {IEEE},
    title = {A Novel Performance Evaluation Methodology for {Single-Target} Trackers},
    url = {http://dx.doi.org/10.1109/tpami.2016.2516982},
    volume = {38},
    year = {2016}
}
Back to publication list