计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 211200133-7.doi: 10.11896/jsjkx.211200133

• 图像处理&多媒体技术 • 上一篇    下一篇

基于SiameseFC的双模板异步更新追踪方法

马汉达, 殷达   

  1. 江苏大学计算机科学与通信工程学院 江苏 镇江 212013
  • 出版日期:2022-11-10 发布日期:2022-11-21
  • 通讯作者: 马汉达(mahd@ujs.edu.cn)

Dual Template and Asynchronous Update Tracking Method Based on SiameseFC

MA Han-da, YIN Da   

  1. School of Computer Science and Communication Engineering,Jiangsu University,Zhenjiang,Jiangsu 212013,China
  • Online:2022-11-10 Published:2022-11-21
  • About author:MA Han-da,born in 1966,master,professor.His main research interests include data mining,big data technology research and applications.

摘要: 全卷积孪生神经网络SiameseFC有着追踪速度快、精度高等优势,但在较为复杂的场景下仍然存在一定的缺陷,并且模板不更新的追踪模式也会在快速变化下的场景中出现较大的误差。因此,提出了一种基于全卷积孪生神经网络的双模板异步更新的追踪算法。首先基于VGG-16网络提取深层与浅层两种特征,分别使用两套对应的模板,两套模板独立且异步地更新,从而节约计算资源。然后对于模板的更新,同时考虑初始模板、前一次追踪所用模板,以及前一帧追踪结果提取的模板,并且使用了基于APCE的判断机制,更新时动态地分配三者的比例。所提算法在OTB100的基准测试结果上优于SiamRPN和SiamDW等主流算法,成功率与精确度均提升了约4%~5%,并且速度达到了44 fps左右,可以满足实时追踪的要求。

关键词: SiameseFC, VGG-16网络, 模板更新, 双模板, APCE

Abstract: SiameseFC has the advantages of fast tracking speed and high accuracy,but it still has some defects in complex scenes,and the tracking mode without updating the template will also cause large errors in the scene that changes rapidly.Therefore,this paper proposes a new tracking method,the dual-template asynchronous update based on SiameseFC.Firstly,both the deep and shallow features are extracted from the VGG-16 network,and two sets of corresponding templates are used respectively,the two sets of templates are updated independently and asynchronously to save computing resources.Then,for the update of the template,the initial template,the template used in the previous tracking,and the template extracted from the tracking result of the previous frame are considered at the same time.And it uses an APCE-based judgment mechanism to dynamically allocate the proportions of the three templatets when updating.This algorithm is superior to mainstream algorithms such as SiamRPN in the benchmark results of OTB100,the success rate and accuracy improve by about 4%~5%,and reaches about 44 fps,which is sufficient to meet real-time tracking requirements.

Key words: SiameseFC, VGG-16, Template update, Dual-template, APCE

中图分类号: 

  • TP391.4
[1]HOU Z Q,HAN C Z.A Survey of Visual Tracking[J].ActaAutomatica Sinica,2006(4):603-617.
[2]GAO W,ZHU M,HE B G,et al.Overview of target trackingtechnology[J].Chinese Optics,2014,7(3):365-375.
[3]BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//The Twenty-Third IEEE Conference on Computer Vision and PattenRecognition(CVPR 2010).San Francisco,CA,USA:IEEE,2010:2544-2550.
[4]MA C,HUANG J B,YANG X,et al.Robust Visual Tracking via Hierarchical Convolutional Features[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(11):2709-2723.
[5]QI Y,ZHANG S,QIN L,et al.Hedged Deep Tracking[C]//Computer Vision & Pattern Recognition.IEEE,2016:4303-4311.
[6]BERTINETTO L,VALMADRE J,HENRIQUES J F,et al.Fully-Convolutional Siamese Networks for Object Tracking[C]//European Conference on Computer Vision.Cham:Sprin-ger,2016.
[7]LI Y,ZHANG X.SiamVGG:Visual Tracking using Deeper Siamese Networks[J].arXiv:1902.02804,2019.
[8]BO L,YAN J,WEI W,et al.High Performance Visual Tracking with Siamese Region Proposal Network[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2018.
[9]LI B,WU W,WANG Q,et al.SiamRPN++:Evolution of Siamese Visual Tracking With Very Deep Networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2020,32(10):4475-4489.
[10]ZHANG Z,PENG H.Deeper and Wider Siamese Networks for Real-Time Visual Tracking[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2020.
[11]HOU Z Q,CHEN L L,YU W S,et al.Robust Visual Tracking Algorithm Based on Siamese Network with Dual Templates[J].Journal of Electronics & Informational Technology,2019,41(9):2247-2255.
[12]SONG J H,ZHANG J,LIU Y J,et al.Conditional generative adversarial siamese networks for object tracking[J].Control and Decision,2021,36(5):1110-1118.
[13]CHEN F J,XIE W X.SiamVGG Network Target Tracking Algorithm with Anti-occlusion Mechanism[J].Signal Processing,2020,36(4):562-571.
[14]REN L C,YANG J Q,WEI Y X,et al.Tracking algorithm using siamese network based on feature fusion and dual-template nested update[J].Computer Engineering,2021,47(7):239-248.
[15]ZHAO F,ZHANG T,WU Y,et al.Antidecay LSTM for Siamese Tracking With Adversarial Learning[J].IEEE Transactions on Neural Networks and Learning Systems,2020,32(10):4475-4489.
[16]WANG M,LIU Y,HUANG Z.Large Margin Object Tracking with Circulant Feature Maps[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2017:4800-4808.
[17]DANELLJAN M,HAGER G,KHAN F S,et al.Learning Spatially Regularized Correlation Filters for Visual Tracking[C]//2015 IEEE International Conference on Computer Vision(ICCV).IEEE,2015.
[18]VALMADRE J,BERTINETTO L,HENRIQUES J F,et al.End-to-End Representation Learning for Correlation Filter Based Tracking[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2017.
[1] 程旭, 崔一平, 宋晨, 陈北京, 郑钰辉, 史金钢.
基于时空注意力机制的目标跟踪算法
Object Tracking Algorithm Based on Temporal-Spatial Attention Mechanism
计算机科学, 2021, 48(4): 123-129. https://doi.org/10.11896/jsjkx.200800164
[2] 陈双叶,王善喜.
基于五帧差分和改进的Meanshift算法的运动目标跟踪
Moving Object Tracking Based on Five Frame Difference and Improved Meanshift Algorithm
计算机科学, 2016, 43(Z6): 203-206. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.048
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!