基于注意力机制的在线自适应孪生网络跟踪算法  

Online Adaptive Siamese Network Tracking Algorithm Based on Attention Mechanism

作　　者：董吉富 刘畅[1] 曹方伟 凌源 高翔 Dong Jifu;Liu Chang;Cao Fangwei;Ling Yuan;Gao Xiang(College of Information Sciences and Technology,Dalian Maritime University,Dalian Liaoning 116026 China;Hualu Zhida Technology Co.,Ltd.,Dalian Liaoning 116023 China)

机构地区：[1]大连海事大学信息科学技术学院,辽宁大连116026 [2]华录智达科技有限公司,辽宁大连116023

出　　处：《激光与光电子学进展》2020年第2期313-321,共9页Laser & Optoelectronics Progress

基　　金：国家科技支撑计划子课题(2015BAG20B02);辽宁省博士启动基金(201601065)。

摘　　要：针对全卷积孪生(SiamFC)网络算法在相似目标共存和目标外观发生显著变化时跟踪失败的问题,提出一种基于注意力机制的在线自适应孪生网络跟踪算法(AAM-Siam)来增强网络模型的判别能力,实现在线学习目标外观变化并抑制背景。首先,分别在模板分支和搜索分支中加入前一帧跟踪所得到的结果,弥补网络在应对目标外观变化的不足;然后通过在孪生网络中加入空间注意力模块和通道注意力模块实现不同帧之间的特征融合,从而在线学习目标形变并抑制背景,进一步提升模型的特征表达能力;最后,在OTB和VOT2016跟踪基准库上进行实验。实验结果表明,本文算法在OTB50数据集上的精确度和平均成功率比基础算法SiamFC分别高出了4.3个百分点和3.6个百分点。This study aims at resolving the tracking failure caused by the coexistence of similar targets and the significant change in the appearance of a target based on the full convolution siamese(SiamFC)network algorithm.An online adaptive siamese network tracking algorithm(AAM-Siam)based on attention mechanism is proposed to enhance the discriminative ability of the network model and achieve the online learning target appearance change and suppress background.Firstly,the results obtained by tracking the previous frame are added into the template branch and the search branch respectively to compensate for the shortcomings of the network by responding to the changes in the appearance of the target.Secondly,the spatial attention module and the channel attention module are employed into the siamese network to achieve the feature fusion among various frames,learn the target deformation online and suppress background,as well as enhancing the model’s ability to express features.Finally,detailed experiments are conducted on the online tracking benchmark(OTB)and visual object tracking 2016(VOT2016)benchmark.The experimental results indicate that the accuracy and average success rate of the proposed algorithm on the OTB50 dataset are 4.3 and 3.6 percentage points higher than those obtained using the basic SiamFC network algorithm,respectively.

关 键 词：机器视觉 孪生网络 注意力机制 卷积神经网络 视觉跟踪 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]