基于动态权重的双分支孪生网络目标跟踪算法  

Object tracking algorithm based on dynamic weight in dual branch siamese network

作　　者：韩萍 王皓韡 方澄 HAN Ping;WANG Haowei;FANG Cheng(College of Electronic Information and Automation,CAUC,Tianjin 300300,China;College of Computer Science and Technology,CAUC,Tianjin 300300,China)

机构地区：[1]中国民航大学电子信息与自动化学院,天津300300 [2]中国民航大学计算机科学与技术学院,天津300300

出　　处：《中国民航大学学报》2022年第5期15-22,共8页Journal of Civil Aviation University of China

基　　金：中国民航大学科研启动基金项目(2017QD05S);中央高校基本科研业务费专项(3122018C005)。

摘　　要：以基于全卷积孪生网络的目标跟踪(SiamFC,fully-convolutional siamese networks for object tracking)算法为代表的部分深度孪生网络目标跟踪算法均是针对目标外观信息进行设计的,易受高速移动、运动模糊、光照变化等因素的影响,造成跟踪目标漂移或丢失。为了提高算法对目标外观变化的适应能力,给出一种基于动态权重的双分支孪生网络目标跟踪算法,以替换特征提取网络后的SiamFC算法作为外观分支,在此基础上增加利用双重注意力强化信息提取的语义分支作为外观分支的有效补充。跟踪阶段利用动态权重系数结合两分支的跟踪结果,有效抑制了目标外观变化对跟踪算法的影响,提升了算法的跟踪精度和鲁棒性。在4个标准目标跟踪数据集OTB2015、UAV20L、UAV123和GOT-10k上验证了本文算法的有效性,平均跟踪帧率为47帧/s,满足跟踪实时性要求。Some of siamese tracking algorithms represented by SiamFC are designed for target appearance information.However,appearance information is easily affected by factors such as high-speed movement,motion blur,and illumination changes,resulting in tracking drift or target loss.In order to improve the ability of the algorithm to adapt target appearance changes,this paper adopts a dual-branch siamese network tracking algorithm based on dynamic weights.Based on improved SiamFC algorithm as the appearance branch,a semantic branch using dual attention mechanism to enhance information extraction is added as an effective supplement.In the tracking stage,a dynamic weight is used to fuse the tracking results of the two branches,which effectively suppresses the influence of target appearance changes,also improves the tracking accuracy and robustness of the algorithm.Our algorithm has been validated on four standard object tracking data sets(OTB2015,UAV123,UAV20L,GOT-10k).The average tracking frame rate is 47 frames/s,which meets the real-time tracking requirements.

关 键 词：视频目标跟踪 孪生网络 注意力机制 动态权重 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]