基于核函数的目标跟踪系统建模与仿真  

Modeling and Simulation of Object Tracking System Based on Kernel Function

作　　者：甘志英 GAN Zhi-ying(Intelligence and Information Engineering College,Tangshan University,Tangshan 063000,China)

机构地区：[1]唐山学院智能与信息工程学院,河北唐山063000

出　　处：《唐山师范学院学报》2023年第6期78-82,共5页Journal of Tangshan Normal University

基　　金：河北省高等学校科学技术研究项目(QN2022186)。

摘　　要：针对目标跟踪中的快速运动、旋转、遮挡等问题,采用核函数算法实现目标跟踪。利用卷积实现密集采样,使用高斯核函数岭回归估计目标位置,在线更新高斯模型和核相关滤波器。通过OTB数据集对算法进行实验验证,结果表明,算法Precision能达到69.7%,Success达到66.8%,跟踪速度达412fps。实验表明,算法在跟踪过程中可对旋转、模糊、遮挡图像中的目标进行有效跟踪,在多个指标上优于其它比较算法。In order to solve the problems of fast motion,rotation and occlusion in target tracking,kernel function algorithm is used to realize target tracking.Dense sampling is realized by convolution,target location is estimated by Gaussian kernel ridge regression,update gaussian model and kernel correlation filter.The performance of the proposed algorithm is tested in OTB dataset.The accuracy is 81.7%,the success rate is 69.2%,and the speed of tracking is 412fps.Experimental results show that the algorithm can effectively track the target in the rotate,fuzzy,occlusion image.The performance is better than other comparison algorithms in many indicators.

关 键 词：目标跟踪 核函数 机器视觉 

分 类 号：TP274.2[自动化与计算机技术—检测技术与自动化装置]