Open AccessDCF with high‐speed spatial constraint
Author(s) -
Liu Jiaqi,
Bai Lianfa,
Zhang Yi,
Han Jing
Publication year - 2019
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2018.5490
Subject(s) - constraint (computer aided design) , discriminative model , benchmark (surveying) , convolution (computer science) , computer science , boundary (topology) , pattern recognition (psychology) , tracking (education) , sample (material) , algorithm , artificial intelligence , mathematics , geometry , psychology , mathematical analysis , pedagogy , chemistry , geodesy , chromatography , artificial neural network , geography
Spatially regularised discriminative correlation filters (SRDCFs) introduce spatial regularisation weights to mitigate the boundary effects caused by circular convolution which obtains superior performance. However, spatial regularisation is computationally expensive; this limits the real‐time performance of SRDCF. This study proposes high‐speed spatial constraint to DCFs (HSCDCFs) for tracking. Using a large area of the sample to learn a CF, then, the authors introduce the spatial constraint to penalise CF coefficients. Their method formulation allows the CFs to efficiently learn a mass of negative samples and high‐quality positive samples. They perform experiments on two benchmark datasets: OTB‐2013 and OTB‐2015. Compared to SRDCF, they provide a slightly reduce of 2.7 and 3.1%, respectively, in mean overlap precision, their method obtains the real‐time speed of 62.5 fps which is ten times faster than SRDCF.