Learning Spatially Regularized Correlation Filters for Visual Tracking

TL;DR

This paper introduces Spatially Regularized Discriminative Correlation Filters (SRDCF) for visual tracking, which improves model quality by penalizing filter coefficients based on spatial location, leading to state-of-the-art results.

Contribution

The paper proposes a novel spatial regularization technique for correlation filters, enabling learning on larger negative sample sets without corrupting positives, and introduces an efficient optimization method.

Findings

Achieves state-of-the-art results on four benchmark datasets.

Improves mean overlap precision by over 8% on OTB-2013 and OTB-2015.

Effectively reduces boundary effects in correlation filter-based tracking.

Abstract

Robust and accurate visual tracking is one of the most challenging computer vision problems. Due to the inherent lack of training data, a robust approach for constructing a target appearance model is crucial. Recently, discriminatively learned correlation filters (DCF) have been successfully applied to address this problem for tracking. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on all patches in the target neighborhood. However, the periodic assumption also introduces unwanted boundary effects, which severely degrade the quality of the tracking model. We propose Spatially Regularized Discriminative Correlation Filters (SRDCF) for tracking. A spatial regularization component is introduced in the learning to penalize correlation filter coefficients depending on their spatial location. Our SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples. We further propose an optimization strategy, based on the iterative Gauss-Seidel method, for efficient online learning of our SRDCF. Experiments are performed on four benchmark datasets: OTB-2013, ALOV++, OTB-2015, and VOT2014. Our approach achieves state-of-the-art results on all four datasets. On OTB-2013 and OTB-2015, we obtain an absolute gain of 8.0% and 8.2% respectively, in mean overlap precision, compared to the best existing trackers.