Now you see me: evaluating performance in long-term visual tracking

TL;DR

This paper introduces a new evaluation methodology and dataset for long-term visual tracking, emphasizing the importance of model update strategies and re-detection capabilities, and provides comprehensive benchmarking of state-of-the-art trackers.

Contribution

It presents a novel long-term tracking evaluation framework, a challenging dataset, and integrates these into the VOT toolkit for standardized benchmarking.

Findings

Model update strategy is crucial for long-term tracking.

Re-detection capability significantly improves tracking performance.

The new methodology effectively differentiates tracker robustness.

Abstract

We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances. We perform an extensive evaluation of six long-term and nine short-term state-of-the-art trackers, using new performance measures, suitable for evaluating long-term tracking - tracking precision, recall and F-score. The evaluation shows that a good model update strategy and the capability of image-wide re-detection are critical for long-term tracking performance. We integrated the methodology in the VOT toolkit to automate experimental analysis and benchmarking and to facilitate the development of long-term trackers.