Learning Padless Correlation Filters for Boundary-effect Free Tracking
Date
2018
Authors
Li, Dongdong
Wen, Gongjian
Kuai, Yangliu
Porikli, Fatih
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers (IEEE Inc)
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.
Description
Keywords
Citation
Collections
Source
IEEE Sensors Journal
Type
Journal article
Book Title
Entity type
Access Statement
Open Access
License Rights
Restricted until
2037-12-31
Downloads
File
Description