SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking

TL;DR

SPSTracker introduces a novel response suppression method that enhances object tracking robustness by reducing sub-peak interference, outperforming existing real-time trackers on multiple benchmarks.

Contribution

The paper proposes a systematic rectified online learning approach with Peak Response Pooling and Boundary Response Truncation to suppress sub-peaks and improve tracking accuracy.

Findings

Outperforms state-of-the-art trackers on OTB, NFS, and VOT2018 benchmarks.

Effectively suppresses sub-peak interference in response maps.

Enhances robustness and accuracy in challenging tracking scenarios.

Abstract

Modern visual trackers usually construct online learning models under the assumption that the feature response has a Gaussian distribution with target-centered peak response. Nevertheless, such an assumption is implausible when there is progressive interference from other targets and/or background noise, which produce sub-peaks on the tracking response map and cause model drift. In this paper, we propose a rectified online learning approach for sub-peak response suppression and peak response enforcement and target at handling progressive interference in a systematic way. Our approach, referred to as SPSTracker, applies simple-yet-efficient Peak Response Pooling (PRP) to aggregate and align discriminative features, as well as leveraging a Boundary Response Truncation (BRT) to reduce the variance of feature response. By fusing with multi-scale features, SPSTracker aggregates the response distribution of multiple sub-peaks to a single maximum peak, which enforces the discriminative capability of features for robust object tracking. Experiments on the OTB, NFS and VOT2018 benchmarks demonstrate that SPSTrack outperforms the state-of-the-art real-time trackers with significant margins.