CVApr 19, 2018

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

arXiv:1804.07056v167 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the need for better evaluation in long-term visual tracking, which is incremental as it builds on existing tracking methods and datasets.

The authors tackled the problem of evaluating long-term visual tracking by proposing a new performance evaluation methodology and a challenging dataset with many target disappearances, resulting in the identification that a good model update strategy and image-wide re-detection capability are critical for performance.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes