Part-based Tracking by Sampling

TL;DR

This paper introduces a novel part-based object tracking method that segments objects into patches, models their color distributions, and tracks them through affine transformations, achieving superior performance on benchmark datasets.

Contribution

The paper presents a new part-based tracking approach with a unique patch placement and color modeling strategy, outperforming existing methods on standard benchmarks.

Findings

Achieves higher performance than all other part-based trackers on VOT2018 and OTB100.

Patch placement scheme significantly improves tracking accuracy.

Local optimization of patch locations enhances robustness.

Abstract

We propose a novel part-based method for tracking an arbitrary object in challenging video sequences. The colour distribution of tracked image patches on the target object are represented by pairs of RGB samples and counts of how many pixels in the patch are similar to them. Patches are placed by segmenting the object in the given bounding box and placing patches in homogeneous regions of the object. These are located in subsequent image frames by applying non-shearing affine transformations to the patches' previous locations, locally optimising the best of these, and evaluating their quality using a modified Bhattacharyya distance. In experiments carried out on VOT2018 and OTB100 benchmarks, the tracker achieves higher performance than all other part-based trackers. An ablation study is used to reveal the effectiveness of each tracking component, with largest performance gains found when using the patch placement scheme.