计算机工程与应用2024，Vol.60Issue(11)：139-146,8.DOI:10.3778/j.issn.1002-8331.2302-0314
基于改进FairMOT的多目标跟踪算法
Multi-Object Tracking Algorithm Based on Improved FairMOT
摘要
Abstract
In response to problems such as missed detections and unfriendly data association algorithms leading to fre-quent switching among objects in complex environments,a multi-object tracking algorithm MFMOT that utilizes the FairMOT framework as its foundation is proposed.Firstly,a lightweight multi-branch attention module is designed,which utilizes channel grouping to reduce complexity and enhances features from three dimensions,enabling the network to select and extract feature information.Secondly,the re-identification branch uses the PolyLoss loss function to enhance the semantic information between similar objects to distinguish different objects of the same type.Finally,a multi-feature fusion simi-larity matrix is proposed to obtain the optimal similarity matrix by fusing multiple feature similarity matrices,reducing the number of identity switches between targets.The experimental results show that the HOTA scores are 61.5%and 56.1%in the MOT17 and MOT20 datasets respectively,which improves by 2.2 percentage points and 2.3 percentage points compared to the original FairMOT model.Furthermore,when applying the multi-feature fusion similarity matrix to a multi-object tracking method with the same mode as FairMOT,improvements in HOTA,MOTA,and IDF1 are observed.关键词
多目标跟踪/重识别/注意力机制/相似度矩阵Key words
multi-object tracking/re-identification/attention mechanism/similarity matrix分类
信息技术与安全科学引用本文复制引用
李旺,张娜娜..基于改进FairMOT的多目标跟踪算法[J].计算机工程与应用,2024,60(11):139-146,8.基金项目
国家自然科学基金(51809163) （51809163）
上海科学技术委员会(19DZ22048) （19DZ22048）
上海市教育委员会"晨光计划"资金项目(AASH1702). （AASH1702）
