中文摘要：

利用核相关滤波器跟踪框架,提出一种改进的自适应颜色属性的目标跟踪方法.首先,构建循环样本矩阵,引进颜色属性作为特征描述目标;然后,采用流行学习局部线性嵌入（LLE）算法自适应地对特征向量进行降维,得到低维特征空间;最后,根据正则化最小二乘分类器获得目标位置.实验结果表明：文中算法的平均中心位置误差减少了21.29px;在阈值为20px时,平均距离精度提高了27.9%,平均跟踪速度为38帧·s~（-1）;与传统核相关滤波（KCF）算法相比,文中算法具有良好的光照不敏感性及更高的跟踪精度和鲁棒性.

英文摘要：

An improved adaptive color attribute tracking algorithm is proposed based on the kernel correlation filter.Firstly,the cycle matrix is established,and color attribute is used to describe the target.Secondly,the local linear embedding（LLE）algorithm was applied to reduce the dimension of extracted feature to achieve a low-dimensional feature space.Finally,the position is obtained by learning the regularized least-squares classifiers.Experimental results demonstrate that the proposed algorithm reduces the median center location error by 21.29 px,the average distance precision is increased by 27.9% when the threshold is set 20 px,and the average tracking speed is 38frames·s（-1）.Compared with the original kernelized correlation filters（KCF）algorithm,the proposed algorithm not only has well illumination insensitivity,but also has higher tracking accuracy and robustness.