1 最小二乘法求解矩阵形式推导 设训练样本集为 ( x i , y i ) (x_i,y_i) (xi,yi),一元(向量)线性回归可表示为: f ( x i ) = w T x i ⃗ + b f(x_i)=w^T\vec{x_i}+b f(xi)=wTxi +b若把样本输入 x i ⃗ \vec{x_i} xi 表示成矩阵形式(设有n个样本输入,每个输入有d个特性),有
Henriques, João F., et al. “High-speed tracking with kernelized correlation filters.” Pattern Analysis and Machine Intelligence, IEEE Transactions on 37.3 (2015): 583-596. 本文的跟踪方法效果甚好,速度奇高,思想和
KCF算法链接:http://www.robots.ox.ac.uk/~joao/circulant/ OTB链接:http://cvlab.hanyang.ac.kr/tracker_benchmark/ 注:matlab版本的 1. Empty format character vector is not supported at the end of a file. Human4.