Online selection of discriminative tracking features

TLDR

The study develops an online feature selection method that dynamically chooses discriminative features to enhance mean‑shift tracking performance. It evaluates candidate features by computing log‑likelihood ratios of object versus background densities, ranks them with a two‑class variance ratio, and selects the top features within a mean‑shift tracker. Experiments show the approach adapts to changing object and background appearances, but is vulnerable to spatially correlated clutter, prompting a secondary strategy to reduce distraction.

Abstract

This paper presents an online feature selection mechanism for evaluating multiple features while tracking and adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that best discriminate between object and background are also best for tracking the object. Given a set of seed features, we compute log likelihood ratios of class conditional sample densities from object and background to form a new set of candidate features tailored to the local object/background discrimination task. The two-class variance ratio is used to rank these new features according to how well they separate sample distributions of object and background pixels. This feature evaluation mechanism is embedded in a mean-shift tracking system that adaptively selects the top-ranked discriminative features for tracking. Examples are presented that demonstrate how this method adapts to changing appearances of both tracked object and scene background. We note susceptibility of the variance ratio feature selection method to distraction by spatially correlated background clutter and develop an additional approach that seeks to minimize the likelihood of distraction.