Visual Tracking with Similarity Matching Ratio

TL;DR

This paper introduces the Similarity Matching Ratio (SMR), a robust visual tracking method that converts pixel differences into probabilities, effectively handling outliers and appearance changes, and achieves state-of-the-art results.

Contribution

The paper proposes SMR, a novel tracking approach that enhances robustness by focusing on pixel similarities below a threshold, differing from traditional difference minimization methods.

Findings

SMR tracker is robust to outliers and appearance changes.

Achieved state-of-the-art performance on challenging sequences.

Outperforms traditional tracking methods in robustness and accuracy.

Abstract

This paper presents a novel approach to visual tracking: Similarity Matching Ratio (SMR). The traditional approach of tracking is minimizing some measures of the difference between the template and a patch from the frame. This approach is vulnerable to outliers and drastic appearance changes and an extensive study is focusing on making the approach more tolerant to them. However, this often results in longer, corrective algo- rithms which do not solve the original problem. This paper proposes a novel approach to the definition of the tracking problems, SMR, which turns the differences into a probability measure. Only pixel differences below a threshold count towards deciding the match, the rest are ignored. This approach makes the SMR tracker robust to outliers and points that dramaticaly change appearance. The SMR tracker is tested on challenging video sequences and achieved state-of-the-art performance.