基于改進(jìn)的ResNet網(wǎng)絡(luò)和特征融合的自標(biāo)跟蹤算法

打開(kāi)文本圖片集

Object tracking algorithm based on improved ResNet network and feature fusion

MENG Weijun'，SUN Siwei'，MA Sugang1，2 （1.SchoolofomputerScienceandTechnologyXi’anUniversityofPostsandTelecommunications，Xi'an7，Cina; 2SanxiKeytselii

Abstract：Anobject trackingalgorithmbasedonimprovedResNetnetworkand feature fusion hasbeenproposedon the basisoftheATOM5Oalgorithm，soastoenhancetheobjectfeaturesextractedwithresidualnetworks.Anenhancedbotteneck block，integratingbatch-freenomalzation（BF）andposition-awareircularconvolution（ParC），ismploedwitintheReset-50 backbonenetwork.Thisefectivelybolstersthecaptureofglobalinformationandmitigatestheaccumulationoftrackingdrift.For theextractedfeatures，theatentionfeaturefusionmoduleisusedtofurtherenhancetheexpressionabilityofthefeaturesforthe objectbyfusingthedetailsofshallwfeaturesandthesemanticinformationofdepfeatures.Theproposedalgorithmwas validated with the OTB2015，VOT2018 and LaSOT datasets.Itachieves a success rate and precision of 70.2% and 91.1%， respectively，ontheOTB2015dataset，whichisimprovedby1.2%and1.5%，respectively，overthebenchmarkATOM50 algorithm. On the VOT2O18 dataset， its expected average overlap rate saw an increase of 4.4% . On the LaSOT dataset，its success rateand precisionareimprovedby2.4%and2.9%，respectively.Itsaverage tracking spedontheOTB2015dataset reaches 34.3 f/s，ensuring real-time tracking.

Keywords：deep learning;visual tracking; Siamese network;batch normalization;attention mechanism;improved ResNet network

0 引言

目標(biāo)跟蹤是計(jì)算機(jī)視覺(jué)領(lǐng)域的核心問(wèn)題之一，其目的是給定第一幀的單個(gè)目標(biāo)，在后續(xù)幀中找到與被跟蹤目標(biāo)最匹配的區(qū)域，并以矩形框的形式表示目標(biāo)的大小和位置。（剩余14508字）