A Novel Performance Evaluation Methodology for Single-Target Trackers

TL;DR

This paper introduces a new, interpretable evaluation methodology for single-target trackers, including a diverse, fully-annotated dataset and a multi-platform system, demonstrated on the large VOT2014 benchmark.

Contribution

It proposes a simple, statistically sound evaluation framework and a highly diverse annotated dataset for improved tracker comparison.

Findings

Most state-of-the-art trackers outperform baselines

The dataset's visual diversity enhances evaluation robustness

The new visualization aids in comparing tracker performance

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.