Correlation Tracking via Robust Region Proposals

TL;DR

This paper introduces an adaptive region proposal scheme for correlation filter-based visual tracking, improving robustness against occlusion, viewpoint change, and model drift, with promising results on challenging sequences.

Contribution

It proposes a novel tracking monitoring indicator and integrates detection and scale proposals to enhance correlation filter trackers.

Findings

Performs favorably against state-of-the-art trackers on challenging sequences.

Effectively recovers from model drift and handles aspect ratio variations.

Improves robustness in occlusion and viewpoint change scenarios.

Abstract

Recently, correlation filter-based trackers have received extensive attention due to their simplicity and superior speed. However, such trackers perform poorly when the target undergoes occlusion, viewpoint change or other challenging attributes due to pre-defined sampling strategy. To tackle these issues, in this paper, we propose an adaptive region proposal scheme to facilitate visual tracking. To be more specific, a novel tracking monitoring indicator is advocated to forecast tracking failure. Afterwards, we incorporate detection and scale proposals respectively, to recover from model drift as well as handle aspect ratio variation. We test the proposed algorithm on several challenging sequences, which have demonstrated that the proposed tracker performs favourably against state-of-the-art trackers.