Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Learning Background-Aware Correlation Filters for Visual Tracking

About

Correlation Filters (CFs) have recently demonstrated excellent performance in terms of rapidly tracking objects under challenging photometric and geometric variations. The strength of the approach comes from its ability to efficiently learn - "on the fly" - how the object is changing over time. A fundamental drawback to CFs, however, is that the background of the object is not be modelled over time which can result in suboptimal results. In this paper we propose a Background-Aware CF that can model how both the foreground and background of the object varies over time. Our approach, like conventional CFs, is extremely computationally efficient - and extensive experiments over multiple tracking benchmarks demonstrate the superior accuracy and real-time performance of our method compared to the state-of-the-art trackers including those based on a deep learning paradigm.

Hamed Kiani Galoogahi, Ashton Fagg, Simon Lucey• 2017

Related benchmarks

TaskDatasetResultRank
Visual TrackingVOT 2016 (test)
EAO0.223
70
Visual Object TrackingVOT 2015--
61
RGBT TrackingRGBT-210
Precision Rate61.6
54
Visual Object TrackingOTB 2015 (test)--
47
Visual Object TrackingOTB100 (test)
AUC0.621
41
Long-term Visual TrackingOxUvALT (test)
MaxGM28.1
26
Visual Object TrackingTC128 (test)--
26
Visual TrackingOTB 2015 (full)
Mean Overlap Precision77.5
23
Visual TrackingVOT 2015 (test)
Accuracy59
20
Visual Object TrackingOTB50 (test)--
20
Showing 10 of 23 rows

Other info

Follow for update