Data Processing Algorithm Based on SVM and GM-PHD in Dense Clutter Environment
WU Zhongming
GUO Jianhui
LOU Genquan
ZHANG Wenjun
Abstract：The problem of multi-target tracking(MTT)in a dense clutter environment has always been a difficult research point.Currently,the probability hypothesis density filtering(PHDF)algorithm is a hot research direction.In order to solve the prob-lem that the complexity and the error rate of GM-PHD increase significantly with strong clutter,an improved algorithm is proposed.Before using GM-PHD to calculate and update the target,the support vector machine technology is used to classify the measure-ment data.Through this technology,valid target data is retained while filtering clutter data as much as possible.The findings demon-strate that the algorithm effectively reduces the computational complexity,suppress clutter and improve tracking performance.
Keywords：target trackingPHDSVMdata processingdata association
Publication Date：2023-10-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 2309-2312,2383 )