Staple: Complementary Learners for Real-Time Tracking

CVPR 2016  ·  Luca Bertinetto, Jack Valmadre, Stuart Golodetz, Ondrej Miksik, Philip Torr ·

Correlation Filter-based trackers have recently achieved excellent performance, showing great robustness to challenging situations exhibiting motion blur and illumination changes. However, since the model that they learn depends strongly on the spatial layout of the tracked object, they are notoriously sensitive to deformation... Models based on colour statistics have complementary traits: they cope well with variation in shape, but suffer when illumination is not consistent throughout a sequence. Moreover, colour distributions alone can be insufficiently discriminative. In this paper, we show that a simple tracker combining complementary cues in a ridge regression framework can operate faster than 80 FPS and outperform not only all entries in the popular VOT14 competition, but also recent and far more sophisticated trackers according to multiple benchmarks. read more

PDF Abstract CVPR 2016 PDF CVPR 2016 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Visual Object Tracking TrackingNet STAPLE_CA Precision 46.72 # 10
Normalized Precision 60.84 # 10
Accuracy 53.59 # 8

Methods


No methods listed for this paper. Add relevant methods here