计算机科学 ›› 2022, Vol. 49 ›› Issue (3): 163-169.doi: 10.11896/jsjkx.210300066

• 计算机图形学&多媒体 • 上一篇    下一篇

基于互注意力指导的孪生跟踪算法

赵越, 余志斌, 李永春   

  1. 西南交通大学电气学院 成都611756
  • 收稿日期:2021-03-08 修回日期:2021-04-13 出版日期:2022-03-15 发布日期:2022-03-15
  • 通讯作者: 余志斌(zbyu@swjtu.edu.cn)
  • 作者简介:(zy5910@my.swjtu.edu.cn)
  • 基金资助:
    装备预研领域基金(61403120304)

Cross-attention Guided Siamese Network Object Tracking Algorithm

ZHAO Yue, YU Zhi-bin, LI Yong-chun   

  1. College of Electronic Engineering,Southwest Jiaotong University,Chengdu 611756,China
  • Received:2021-03-08 Revised:2021-04-13 Online:2022-03-15 Published:2022-03-15
  • About author:ZHAO Yue,born in 1995,postgraduate.His main research interests include artificial intelligence,pattern recognition and computer vision.
    YU Zhi-bin,born in 1977,Ph.D,asso-ciate professor,is a member of China Computer Federation.His main research interests include artificial intelligence,pattern recognition and signal processing.
  • Supported by:
    National Defense Pre-Research Foundation of China(61403120304).

摘要: 针对传统孪生网络目标跟踪算法在相似物干扰、目标形变、复杂背景等跟踪环境下无法进行鲁棒跟踪的问题,提出了注意力机制指导的孪生网络目标跟踪方法,以弥补传统孪生跟踪方法存在的性能缺陷。首先,利用卷积神经网络ResNet50的不同网络层来提取多分辨率的目标特征,并设计互注意力模块使模板分支与搜索分支之间的信息能够相互流动。然后,在分类与回归网络中,将主干网络提取的每块特征信息权重参数通过神经网络自动学习、更新并加权融合每块特征的分类与回归信息。最后,根据响应图的峰值位置计算目标的预估位置和尺度信息。在UAV123数据集上,所提算法相比主流跟踪算法SiamBAN,准确率提升了1.7个点,成功率提升了0.7个点;在VOT2018数据集上,相比SiamRPN++算法,所提算法在EAO指标上提高了2.5个点,实时跟踪速度保持在35FPS。

关键词: 互注意力模块, 孪生网络, 目标跟踪, 无锚框回归, 相似物干扰

Abstract: Most traditional Siamese trackers cannot perform robust when facing the similar object,deformation,background clutters and other challenges.Accordingly,a cross-attention guided Siamese network (called SiamCAN) is proposed to solve the above problem in this paper.Firstly,different layers of ResNet50 are used to get various revolutions of object feature and a cross-attention module is designed to bridge the information flow between search branch and template branch.After that,each feature from different layers of backbone is sent to CNNs to update parameters and combined with each other,in classification network and regression network.Finally,the predicted location and target size are calculated according to the max response on response map.Simulation experimental results on the UAV123 tracking dataset show that the tracking precision is improved by 1.7% and the tracking accuracy is improved by 0.7%,compared to the mainstream algorithm SiamBAN.Moreover,on the VOT2018 benchmark,the EAO of our method outperforms 2.5 than the mainstream algorithm SiamRPN++,and the tracking speed of our method maintains 35FPS.

Key words: Anchor-free regression, Cross-attention module, Siamese network, Similar object distractor, Visual object tracking

中图分类号: 

  • TP391
[1]BERTINETTO L,VALMADRE J,HENRIQUES J F,et al.Fully-convolutional siamese networks for object tracking[C]//European Conference on Computer Vision.Cham:Springer,2016:850-865.
[2]LI B,YAN J,WU W,et al.High performance visual tracking with siamese region proposal network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8971-8980.
[3]ZHU Z,WANG Q,LI B,et al.Distractor-aware siamese net-works for visual object tracking[C]//Proceedings of the European Conference on Computer Vision (ECCV).2018:101-117.
[4]LI B,WU W,WANG Q,et al.Siamrpn++:Evolution of siamese visual tracking with very deep networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:4282-4291.
[5]ZHANG Z,PENG H.Deeper and wider siamese networks for real-time visual tracking[C]//Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.2019:4591-4600.
[6]HE A,LUO C,TIAN X,et al.A twofold siamese network forreal-time object tracking[C]//Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.2018:4834-4843.
[7]ABDELPAKEY M H,SHEHATA M S,MOHAMED M M.Denssiam:End-to-end densely-Siamese network with self-attention model for object tracking[C]//International Symposium on Visual Computing.Cham:Springer,2018:463-473.
[8]WANG Q,TENG Z,XING J,et al.Learning attentions:residual attentional siamese network for high performance online visual tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:4854-4863.
[9]XU Y,WANG Z,LI Z,et al.SiamFC++:Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines[J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):12549-12556.
[10]GUO D,WANG J,CUI Y,et al.SiamCAR:Siamese Fully Con-volutional Classification and Regression for Visual Tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:6269-6277.
[11]CHEN Z,ZHONG B,LI G,et al.Siamese Box Adaptive Network for Visual Tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:6668-6677.
[12]WANG N,SHI J,YEUNG D Y,et al.Understanding and diagnosing visual tracking systems[C]//Proceedings of the IEEE International Conference on Computer Vision.2015:3101-3109.
[13]ZHENG Z,WANG P,LIU W,et al.Distance-IoU Loss:Faster and Better Learning for Bounding Box Regression[C]//AAAI.2020:12993-13000.
[14]REZATOFIGHI H,TSOI N,GWAK J Y,et al.Generalized intersection over union:A metric and a loss for bounding box regression[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:658-666.
[15]RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet LargeScale Visual Recognition Challenge[J].International Journal of Computer Vision,2015,115(3):211-252.
[16]LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft coco:Common objects in context[C]//European Conference on Computer Vision.Cham:Springer,2014:740-755.
[17]REAL E,SHLENS J,MAZZOCCHI S,et al.Youtube-boun-dingboxes:A large high-precision human-annotated data set for object detection in video[C]//proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.2017:5296-5305.
[18]RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet LargeScale Visual Recognition Challenge[J].International Journal of Computer Vision,2015,115(3):211-252.
[19]HUANG L,ZHAO X,HUANG K.Got-10k:A large high-diversity benchmark for generic object tracking in the wild[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019.
[20]MUELLER M,SMITH N,GHANEM B.A Benchmark andSimulator for UAV Tracking[C]//European Conference on Computer Vision.Cham:Springer,2016:445-461.
[21]DANELLJAN M,BHAT G,SHAHBAZ KHAN F,et al.Eco:Efficient convolution operators for tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:6638-6646.
[22]DANELLJAN M,HAGER G,KHAN F S,et al.Learning spatially regularized correlation filters for visual tracking[C]//Proceedings of the IEEE international conference on computer vision.2015:4310-4318.
[23]KRISTAN M,LEONARDIS A,MATAS J,et al.The sixthvisual object tracking vot2018 challenge results[C]//Procee-dings of the European Conference on Computer Vision (ECCV).2018.
[24]BAI S,HE Z,DONG Y,et al.Multi-hierarchical independentcorrelation filters for visual tracking[C]//2020 IEEE International Conference on Multimedia and Expo (ICME).IEEE,2020:1-6.
[25]WANG G,LUO C,SUN X,et al.Tracking by instance detection:A meta-learning approach[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:6288-6297.
[26]DANELLJAN M,BHAT G,KHAN F S,et al.Atom:Accurate tracking by overlap maximization[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:4660-4669.
[1] 陈坤峰, 潘志松, 王家宝, 施蕾, 张锦.
基于双目叠加仿生的微换衣行人再识别
Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation
计算机科学, 2022, 49(8): 165-171. https://doi.org/10.11896/jsjkx.210600140
[2] 沈祥培, 丁彦蕊.
多检测器融合的深度相关滤波视频多目标跟踪算法
Multi-detector Fusion-based Depth Correlation Filtering Video Multi-target Tracking Algorithm
计算机科学, 2022, 49(8): 184-190. https://doi.org/10.11896/jsjkx.210600004
[3] 文成宇, 房卫东, 陈伟.
多目标跟踪的对象初始化综述
Object Initialization in Multiple Object Tracking:A Review
计算机科学, 2022, 49(3): 152-162. https://doi.org/10.11896/jsjkx.210200048
[4] 陈媛, 惠燕, 胡秀华.
一种自适应尺度与学习速率调整的背景感知相关滤波跟踪算法
Background-aware Correlation Filter Tracking Algorithm with Adaptive Scaling and Learning Rate Adjustment
计算机科学, 2021, 48(5): 177-183. https://doi.org/10.11896/jsjkx.200300109
[5] 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
[6] 张开华, 樊佳庆, 刘青山.
视觉目标跟踪十年研究进展
Advances on Visual Object Tracking in Past Decade
计算机科学, 2021, 48(3): 40-49. https://doi.org/10.11896/jsjkx.201100186
[7] 叶阳, 卢奇, 程时伟.
基于质心法的车联网目标跟踪方法与应用
Centroid Method Based Target Tracking and Application for Internet of Vehicles
计算机科学, 2021, 48(11A): 340-344. https://doi.org/10.11896/jsjkx.210200004
[8] 刘彦, 秦品乐, 曾建朝.
基于YOLOv3与分层数据关联的多目标跟踪算法
Multi-object Tracking Algorithm Based on YOLOv3 and Hierarchical Data Association
计算机科学, 2021, 48(11A): 370-375. https://doi.org/10.11896/jsjkx.201000115
[9] 赵钦炎, 李宗民, 刘玉杰, 李华.
基于信息熵的级联Siamese网络目标跟踪
Cascaded Siamese Network Visual Tracking Based on Information Entropy
计算机科学, 2020, 47(9): 157-162. https://doi.org/10.11896/jsjkx.190800160
[10] 程中建, 周双娥, 李康.
基于多尺度自适应权重的稀疏表示目标跟踪算法
Sparse Representation Target Tracking Algorithm Based on Multi-scale Adaptive Weight
计算机科学, 2020, 47(6A): 181-186. https://doi.org/10.11896/JsJkx.190500093
[11] 喻露, 胡剑锋, 姚磊岳.
全局块与局部块协作的相关滤波目标跟踪算法
Correlation Filter Object Tracking Algorithm Based on Global and Local Block Cooperation
计算机科学, 2020, 47(6): 157-163. https://doi.org/10.11896/jsjkx.190500078
[12] 谭建豪, 殷旺, 刘力铭, 王耀南.
采用多相关滤波策略的鲁棒长时自适应目标跟踪
Robust Long-term Adaptive Object Tracking Based onMulti-correlation Filtering Strategy
计算机科学, 2020, 47(12): 169-176. https://doi.org/10.11896/jsjkx.191000021
[13] 张良成, 王运锋.
动态自适应的多雷达信息加权融合方法
Dynamic Adaptive Multi-radar Tracks Weighted Fusion Method
计算机科学, 2020, 47(11A): 321-326. https://doi.org/10.11896/jsjkx.2004000145
[14] 马康, 娄静涛, 苏致远, 李永乐, 朱愿.
结合特征融合和尺度自适应的核相关滤波器目标跟踪算法研究
Object Tracking Algorithm Based on Feature Fusion and Adaptive Scale Kernel Correlation Filter
计算机科学, 2020, 47(11A): 224-230. https://doi.org/10.11896/jsjkx.200500084
[15] 龚轩, 乐孜纯, 王慧, 武玉坤.
多目标跟踪中的数据关联技术综述
Survey of Data Association Technology in Multi-target Tracking
计算机科学, 2020, 47(10): 136-144. https://doi.org/10.11896/jsjkx.200200041
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!