融合记忆信息的单目标跟踪模板更新机制  

Template Update Mechanism for Single Target Tracking Incorporating Memory Information

作　　者：毛昱雯 葛宝臻[1,2] 权佳宁 陈其博 Mao Yuwen;Ge Baozhen;Quan Jianing;Chen Qibo(School of Precision Instrument and OptoElectronics Engineering,Tianjin University,Tianjin 300073,China;Key Laboratory of OptoElectronics Information Technology,Ministry of Education,Tianjin University,Tianjin 300073,China)

机构地区：[1]天津大学精密仪器与光电子工程学院,天津300073 [2]天津大学光电信息技术教育部重点实验室,天津300073

出　　处：《激光与光电子学进展》2024年第8期383-390,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61535008)。

摘　　要：针对孪生架构单目标跟踪算法存在的目标状态更新不及时的问题,基于模板与记忆信息动态融合的跟踪策略,提出一种通用的模板更新机制。该机制采用双模块融合的更新策略:通过记忆融合模块融合搜索图像特征的短期记忆信息,获得目标变化情况;将前一帧可信的跟踪结果作为动态模板,从相关特征的角度,通过权重融合模块对原始模板和动态模板进行加权融合,通过结合跟踪过程的原始记忆与短期记忆实现更准确的目标定位。将模板更新机制应用于SiamRPN、SiamRPN++和RBO三种主流算法,并在VOT2019公开数据集上进行实验验证。结果表明:应用该机制后算法的性能得到了有效提升,具体而言,在SiamRPN++算法中,平均重叠期望值提升了6.67%,准确性提升了0.17%,鲁棒性下降了5.39%;此外,在遮挡、形变和背景干扰等复杂场景下,添加模板更新机制的SiamRPN++算法展现出较好的跟踪性能。Single target tracking algorithm based on Siamese architecture suffers from untimely target state update.To address this issue,a generic template update mechanism is proposed based on the dynamic fusion of templates and memory information.The mechanism uses a dual module fusion update strategy.The shortterm memory information of search feature map is fused using a memory fusion module to capture target variations.The trusted tracking result of the previous frame is used as a dynamic template.The original and dynamic templates are fused using a weight fusion module from the correlated feature perspective to achieve more accurate target localization using the original and shortterm memories during the tracking process.The template update mechanism is applied to three mainstream algorithms,SiamRPN,SiamRPN++and RBO,and experiments are conducted on the VOT2019 public dataset.The results show that the performance of the algorithms is effectively improved after applying the mechanism.Specially,for the SiamRPN++algorithm,the average overlap expectation is improved by 6.67%,the accuracy is improved by 0.17%,and the robustness is enhanced by 5.39%after applying the template update mechanism.In addition,the SiamRPN++algorithm with the mechanism has better tracking performance in complex scenarios with occlusion,deformation and background interference.

关 键 词：目标跟踪 孪生网络 模板更新 记忆信息 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]