Learning Padless Correlation Filters for Boundary-Effect Free Tracking

Abstract

Recently, discriminative correlation filters (DCFs) have achieved enormous popularity in the tracking community due to high accuracy and beyond real-time speed. Among different DCF variants, spatially regularized discriminative correlation filters (SRDCFs) demonstrate excellent performance in suppressing boundary effects induced from circularly shifted training samples. However, SRDCF have two drawbacks which may be the bottlenecks for further performance improvement. First, SRDCF needs to construct an element-wise regularization weight map which can lead to poor tracking performance without careful tunning. Second, SRDCF does not guarantee zero correlation filter values outside the target bounding box. These small but nonzero filter values away from the filter center hardly contribute to target location but induce boundary effects. To tackle these drawbacks, we revisit the standard SRDCF formulation and introduce padless correlation filters (PCFs) which totally remove boundary effects. Compared with SRDCF that penalizes filter values with spatial regularization weights, PCF directly guarantee zero filter values outside the target bounding box with a binary mask. Experimental results on the OTB2013, OTB2015 and VOT2016 data sets demonstrate that PCF achieves real-time frame-rates and favorable tracking performance compared with state-of-the-art trackers.