各CF-based tracker中output_sigma_factor取值

现有的各CF-Based tracker中理想高斯响应中output_sigma_factor的取值情况

默认output_sigma = target_sz*output_sigma_factor;

 

【CREST】 0.1

　　　　output_sigma_factor=0.1;

　　　　output_sigma = target_sz*output_sigma_factor;%output_sigma 是个向量

　　　　labels = exp(-alpha*(rs.^2/sigma(1)^2 + cs.^2/sigma(2)^2));%这里alpha根据不同的情况取0.2或者0.3，具体参见源代码

【KCF】0.1

　　　　output_sigma_factor=0.1;

　　　　output_sigma = sqrt(prod(target_sz)) * output_sigma_factor / cell_size; %output_sigma 是个标量

　　　　labels = exp(-0.5 / sigma^2 * (rs.^2 + cs.^2));

 

 

 

Reference:

【CREST】:Y Song, C Ma, L Gong, et al. CREST Convolutional Residual Learning for Visual Tracking[C]. //ICCV2017

【KCF】: JF Henriques, R Caseiro, P Martins, et al. High-Speed Tracking with Kernelized Correlation Filters[J]. TPAMI2015.