DCF with high-speed spatial constraint

作者：Liu, Jiaqi; Bai, Lianfa^*; Zhang, Yi; Han, Jing

来源：IET Image Processing, 2019, 13(1): 44-48.

DOI：10.1049/iet-ipr.2018.5490

• filtering theory
• convolution
• correlation methods
• real-time speed
• high-speed spatial constraint
• spatial regularisation weights
• real-time performance
• high-quality positive samples
• spatially regularised discriminative correlation filters
• boundary effect mitigation
• circular convolution
• HSCDCF
• OTB-2013 benchmark dataset
• OTB-2015 benchmark dataset

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 62.5fps which is ten times faster than SRDCF.

• 出版日期2019-1
• 单位南京理工大学