摘要
为解决长时目标跟踪场景中由于遮挡、超出视野导致的目标频繁丢失与重现的问题,设计了一种基于模板更新和重检测的长时目标跟踪算法(LTUSiam)。首先,在跟踪器SiamRPN的基础上,引入三级级联的门控循环单元对目标状态进行判断,选择合适的时机自适应更新模板信息。其次,提出一种基于模板匹配的重检测算法,使用候选区域提取模块重定位目标位置和大小,使用评价得分序列对目标丢失的情况进行判断,以确定下一帧的跟踪状态。实验结果显示,LTUSiam在LaSOT数据集上的成功率和准确率分别达到了0.566和0.556,在VOT 2018_LT数据集上的F 1值为0.644,表明其在处理目标丢失与重现问题时有更好的鲁棒性,有效地改善了长时跟踪的性能。
In order to solve the problem of frequent disappearing and reappearing of targets due to occlusion and out of view in long-term target tracking scenes,a long-term target tracking algorithm based on update and redetection(LTUSiam)is designed.Firstly,based on the basic tracker Siamese region proposed network(SiamRPN),a three-level cascade gated cycle unit is introduced to judge the target state and choose the right time to update the template information adaptively.Secondly,a redetection algorithm based on template matching is proposed.The candidate region extraction module is used to relocate the target position and size,and the evaluation score sequence is used to judge the target loss to determine the tracking state of the next frame.Experiments show that the success rate and precision of LTUSiam on LaSOT dataset reach 0.566 and 0.556 respectively,and the F 1-score of L TUSiam on VOT2018_LT dataset is 0.644,which has better robustness in dealing with target loss recurrence problem,and effectively improves the performance of long-term tracking.
作者
徐淑萍
卫浩波
孙洋洋
万亚娟
XU Shu-ping;WEI Hao-bo;SUN Yang-yang;WAN Ya-juan(School of Computer Science and Engineering,Xi’an Technological University,Xi’an 710021,China)
出处
《计算机工程与科学》
CSCD
北大核心
2024年第12期2196-2204,共9页
Computer Engineering & Science
关键词
长时跟踪
孪生网络
模板更新
重检测
long-term tracking
Siamese network
template update
redetection
作者简介
徐淑萍(1974-),女,山西运城人,硕士,教授,研究方向为计算机控制和智能信息处理。E-mail:563937848@qq.com;卫浩波(1992-),男,山西河津人,硕士,研究方向为计算机视觉。E-mail:1459403108@qq.com;孙洋洋(1998-),女,河南洛阳人,硕士,研究方向为计算机视觉。E-mail:2675379281@qq.com;万亚娟(1998),女,河南周口人,硕士,研究方向为计算机视觉。E-mail:1822884334@qq.com。
