SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking
This addresses robust object tracking for computer vision applications, offering an incremental improvement by systematically handling progressive interference.
The paper tackled the problem of model drift in visual object tracking caused by sub-peaks in response maps from interference, proposing SPSTracker to suppress sub-peaks and enforce peak response, resulting in state-of-the-art performance on benchmarks like OTB, NFS, and VOT2018 with significant margins.
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.