基于实时动态模板更新的Transformer目标跟踪方法  

Transformer Object Tracking Method Based on Real-Time Dynamic Template Update

作　　者：孙子文 钱立志 袁广林 杨传栋 凌冲 SUN Ziwen;QIAN Lizhi;YUAN Guanglin;YANG Chuandong;LING Chong(Laboratory of Guidance Control and Information Perception Technology of High Overload Projectiles,Army Academy of Artillery and Air Defense,Hefei 230031,Anhui,China;Computer Teaching and Research Office of Department of Information Engineering,Army Academy of Artillery and Air Defense,Hefei 230031,Anhui,China)

机构地区：[1]陆军炮兵防空兵学院高过载弹药制导控制与信息感知实验室,安徽合肥230031 [2]陆军炮兵防空兵学院信息工程系计算机教研室,安徽合肥230031

出　　处：《计算机工程》2025年第4期158-168,共11页Computer Engineering

摘　　要：基于Transformer的目标跟踪方法广泛应用在计算机视觉领域,并取得了优异的效果。但是,由于在实际跟踪任务中受目标变换、目标遮挡、光照变化以及目标快速运动等因素的影响,导致目标信息发生变化,现有方法对目标模板变化信息利用不足,限制了跟踪性能的提高。为此,通过附加一条动态模板更新分支反映目标最新的外观和运动状态,提出一种基于实时动态模板更新的Transformer目标跟踪方法TransTRDT。该分支通过模板质量评分头对模板是否更新进行判断,当判定可以进行更新时,随后将初始模板、前一帧动态模板以及裁剪后的最新预测结果传入动态模板更新网络中更新动态模板,通过获取更可靠的模板从而实现更准确的目标跟踪。在公共数据集上的实验结果表明,TransTRDT在GOT-10k、LaSOT以及TrackingNet上的跟踪性能优于SwinTrack和StarK等算法,在OTB100中的跟踪成功率为71.9%,跟踪速度为36.82帧/s,达到目前行业的领先水平。Transformer-based object tracking methods are widely used in the field of computer vision and have achieved excellent results.However,object transformations,object occlusion,illumination changes,and rapid object motion can change object information during actual tracking tasks,and consequently,the underutilization of object template change information in existing methods prevents the tracking performance from improving.To solve this problem,this paper presents a Transformer object tracking method,TransTRDT,based on real-time dynamic template update.A dynamic template updating branch is attached to reflect the latest appearance and motion state of an object.The branch determines whether the template is updated through the template quality scoring header;when it identifies the possibility of an update,it passes the initial template,the dynamic template of the previous frame,and the latest prediction after cropping into the dynamic template updating network to update the dynamic template.As a result,the object can be tracked more accurately by obtaining a more reliable template.The tracking performance of TransTRDT on GOT-1ok,LsSOT,and TrackingNet is superior to algorithms such as SwinTrack and StarK.It outperforms to achieve a tracking success rate of 71.9%on the OTB100 dataset,with a tracking speed of 36.82 frames per second,reaching the current leading level in the industry.

关 键 词：目标跟踪 注意力机制 动态模板更新 质量评分头 Transformer目标跟踪 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]