基于高斯尺度空间的核相关滤波目标跟踪算法

摘要

Recently, Kernel Correlation Filter(KCF)has achieved great attention in visual tracking field, which provides excellent computation performance and high possessing speed. However, how to handle the scale variation is still an open problem. Focusing on this issue, a method based on Gaussian scale space is proposed. Firstly, this paper uses KCF to esti-mate the location of the target, the context region which includes the target and its surrounding background will be the image to be matched. In order to get the matching image of a Gaussian scale space, image with Gaussian kernel convolution can be got. After getting the Gaussian scale space of the image to be matched, then, according to the Gaussian scale space image, it estimates target image under different scales. It combines with the scale parameter of scale space, for each corre-sponding scale image performing bilinear interpolation operation to change the size to simulate target imaging at different scales. Finally, matching the template with different size of images with different scales, the paper uses Mean Absolute Difference(MAD)as the match criterion. After getting the optimal matching in the image, it ascertains the best zoom ra-tios, consequently estimates the target size. In the experiments, compare with CSK, KCF, the results demonstrate that the proposed method achieves high improvement in accuracy and is an efficient algorithm.%核相关滤波（KCF）跟踪算法因其计算效率及速度的优势在目标跟踪领域受到了极大关注，但是该算法仍无法实现尺度自适应，针对此问题提出了一种基于高斯尺度空间的解决方法。根据KCF跟踪算法估计目标位置，将目标及其周围的区域作为搜索区域，并与高斯核卷积建立高斯尺度空间。对高斯尺度空间进行双线性插值，得到目标的多尺度估计图像。用平均绝对误差（MAD）作为匹配准则，将模板与图像匹配，从而得到目标的缩放比率。实验结果表明，与CSK算法、KCF算法等相比，所提出的基于高斯尺度空间的KCF在跟踪精确度上有了显著提升。