基于KCF和双目测距的目标跟随系统设计与实现  

Design and Implementation of Target Following System Based on KCF and Binocular Distance Measurement

作　　者：胡智威 杜运本 陈燕 易朵云 姚明智 HU Zhiwei;DU Yunben;CHEN Yan;YI Duoyun;YAO Mingzhi(School of Electronic Information,Jiangsu University of Science and Technology,Zhenjiang 212100)

机构地区：[1]江苏科技大学电子信息学院,镇江212100

出　　处：《计算机与数字工程》2024年第9期2610-2613,2639,共5页Computer & Digital Engineering

摘　　要：针对KCF(核相关滤波算法)对快速运动过程中的物体或在视频帧率较低情况下,稳定性较差的问题。论文在经典KCF算法上结合了双目测距算法,设计并实现了一种目标跟随系统。实验表明,结合KCF和双目测距的算法不仅能够有效提升跟随效果并且满足嵌入式平台的运行要求。Aiming at the problem of poor stability of KCF(kernel correlation filtering algorithm)for fast moving objects or under low video frame rate.In this paper,a target tracking system is designed and implemented by combining the binocular ranging algorithm with the classical KCF algorithm.Experiments show that the algorithm combining KCF and binocular ranging can not only effectively improve the tracking effect but also meet the operation requirements of the embedded platform.

关 键 词：核相关滤波(KCF) 双目测距算法 目标跟随系统 嵌入式平台 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]