ABSTRACT

Objective

To reduce the effects of light changes, scale changes, local occlusion and other factors during target tracking, a kernel-correlation filtering (KCF) target tracking algorithm is introduced, which introduces the target block model.

Results

Comparative experiments of multiple mainstream algorithms on multiple data sets. Experimental results show that the algorithm has the highest accuracy and success rate, which are 11.89% and 15.24% higher than the KCF algorithm, respectively, indicating that the algorithm proposed in this paper possesses a more sensitive response to changes in illumination. Among them, factors such as scale change and local occlusion are more robust.

中文翻译：

---

基于核相关滤波的行人运动目标跟踪算法

摘要

客观的

为了减少目标跟踪过程中光线变化、尺度变化、局部遮挡等因素的影响，引入了核相关滤波（KCF）目标跟踪算法，该算法引入了目标块模型。

结果

多种主流算法在多个数据集上的对比实验。实验结果表明，该算法的准确率和成功率最高，分别比KCF算法高11.89%和15.24%，表明本文提出的算法对光照变化具有更灵敏的响应。其中，尺度变化和局部遮挡等因素更为稳健。