A Low Parameter Real-Time Target Tracking Algorithm Based on Siamese Convolutional Network

doi:10.19678/j.issn.1000-3428.0057076

Abstract

Abstract: The existing target tracking algorithms based on deep learning face deployment problems on embedded devices due to their large number of parameters.To address the problems,this paper proposes a real-time target tracking algorithm based on low parameter siamese convolutional network.By designing an asymmetric convolution module to build the entire network framework,the compression layer of the asymmetric convolution module is used to reduce the number of parameters,and the asymmetric layer is used for feature fusion to reduce the size of the model while maintaining accuracy.At the same time,the triple loss function is used to replace the logical loss function for model training,and the more expressive depth features are extracted for target tracking with the same input,which improves the tracking accuracy of the model.The performance of the algorithm is tested on the GOT-10K,OTB100 and VOT2016 benchmarks.Experimental results show that the algorithm reduces the model size to 3.8×10⁶,and outperforms SiamFC,KCF,DAT and other tracking algorithms in terms of speed and accuracy.

Key words: target tracking, low parameter model, siamese convolutional network, real-time performance, asymmetric convolution, triplet loss

摘要： 针对基于深度学习的目标跟踪算法模型参数多、难以部署于嵌入式设备上的问题，提出一种改进的孪生卷积网络实时目标跟踪算法。设计一个非对称卷积模块来构建整个网络框架，通过非对称卷积模块的压缩层减少模型参数量，利用非对称层进行特征融合，以在保证精度的同时压缩模型大小。使用三元组损失函数代替逻辑损失函数进行模型训练，在输入不变的情况下提取表达性更强的深度特征，从而完成目标跟踪任务并提高模型的跟踪精度。在GOT-10K、OTB100和VOT2016基准上对算法性能进行测试，结果表明，该算法能够将模型大小降为3.8×10⁶，且速度与精度均优于SiamFC、KCF和DAT等跟踪算法。

关键词: 目标跟踪, 低参数模型, 孪生卷积网络, 实时性, 非对称卷积, 三元组损失

CLC Number:

TP391

LUO Shuo, HOU Jin, TAN Guanghong, HAN Yanpeng. A Low Parameter Real-Time Target Tracking Algorithm Based on Siamese Convolutional Network[J]. Computer Engineering, 2021, 47(2): 84-89.

罗朔, 侯进, 谭光鸿, 韩雁鹏. 一种低参数的孪生卷积网络实时目标跟踪算法[J]. 计算机工程, 2021, 47(2): 84-89.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0057076

http://www.ecice06.com/EN/Y2021/V47/I2/84

Figures/Tables 7

References 23

[1]	GUAN Hao,CUI Xiangyang,AN Zhiyong.Advances on application of deep learning for video object tracking[J].Acta Automatica Sinica,2016,42(6):834-847.(in Chinese)管皓,薛向阳,安志勇.深度学习在视频目标跟踪中的应用进展与展望[J].自动化学报,2016,42(6):834-847.
[2]	BOLME D,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:2544-2550.
[3]	LIU Tianjian,QIU Lida,ZHANG Ning.Improved object tracking algorithm based on mean shift[J].Computer Engineering,2015,41(9):281-285.(in Chinese)刘天键,邱立达,张宁.基于均值漂移的改进目标跟踪算法[J].计算机工程,2015,41(9):281-285.
[4]	LEICHTER I.Mean shift trackers with cross-Bin metrics[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):695-706.
[5]	WANG N,YEUNG D Y.Learning a deep compact image representation for visual tracking[EB/OL].[2019-11-10].http://winsty.net/papers/dlt.pdf.
[6]	BERTINETTO L,VALMADRE J,HENRIQUES J F,et al.Fully-convolutional Siamese networks for object tracking[M]//ELGAMMAL A M,HARWOOD D,DAVIS L S.Lecture notes in computer science.Berlin,Germany:Springer,2016:850-865.
[7]	SONG Y B,MA C,GONG L J,et al.CREST:convolu-tional residual learning for visual tracking[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:2574-2583.
[8]	WANG Qiang,TENG Zhu,XING Junliang,et al.Learning attentions:residual attentional Siamese network for high performance online visual tracking[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:4854-4863.
[9]	NAM H,HAN B.Learning multi-domain convolutional neural networks for visual tracking[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:4293-4302.
[10]	LI Bo,YAN Junjie,WU Wei,et al.High performance visual tracking with Siamese region proposal network[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:8971-8980.
[11]	WANG Q,ZHANG L,BERTINETTO L C,et al.Fast online object tracking and segmentation:a unifying approach[EB/OL].[2019-11-10].https://arxiv.org/abs/1812.05050.
[12]	DENTON E,ZAREMBA W,BRUNA J,et al.Exploiting linear structure within convolutional networks for efficient evaluation[EB/OL].[2019-11-10].https://cs.nyu.edu/~denton/papers/compressconv.pdf.
[13]	PASZKE A,CHAURASIA A,KIM S,et al.ENet:a deep neural network architecture for real-time semantic segmentation[EB/OL].[2019-11-10].https://arxiv.org/abs/1606.02147.
[14]	SCHROFF F,KALENICHENKO D,PHILBIN J.FaceNet:a unified embedding for face recognition and clustering[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:815-823.
[15]	SONG H O,XIANG Y,JEGELKA S,et al.Deep metric learning via lifted structured feature embedding[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:4004-4012.
[16]	CHEN Qiaoyuan,CHEN Ying.TriHard loss based multi-task person re-identification[J].Journal of Computer-Aided Design and Computer Graphics,2019,31(7):1156-1165.(in Chinese)陈巧媛,陈莹.基于困难样本三元组损失的多任务行人再识别[J].计算机辅助设计与图形学学报,2019,31(7):1156-1165.
[17]	HUANG Lianghua,ZHAO Xin,HUANG Kaiqi.GOT-10K:a large high-diversity benchmark for generic object tracking in the wild[EB/OL].[2019-11-10].https://arxiv.org/pdf/1810.11981.pdf.
[18]	WU Y,LIM J,YANG M H.Online object tracking:a bench-mark[C]//Proceedings of 2013 IEEE Conference on Com-puter Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:2411-2418.
[19]	KRISTAN M,LEONARDIS A,MATAS J,et al.The visual object tracking VOT2016 challenge results[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2016:236-256.
[20]	WANG Renhua,SHEN Jianyu,JIANG Min.Target tracking algorithm based on adaptive multi-model joint[J].Computer Engineering,2019,45(8):266-274.(in Chinese)王任华,沈剑宇,蒋敏.基于自适应多模型联合的目标跟踪算法[J].计算机工程,2019,45(8):266-274.
[21]	HENRIQUES J F,CASEIRO R,MARTINS P,et al.High-speed tracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(3):583-596.
[22]	LI Yang,ZHU Jianke.A scale adaptive kernel correlation filter tracker with feature integration[EB/OL].[2019-11-10].http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/ECCV_2014/workshops/w09/W9-07.pdf.
[23]	CEHOVIN L,LEONARDIS A,KRISTAN M.Robust visual tracking using template anchors[C]//Proceedings of 2016 IEEE Winter Conference on Applications of Computer Vision.Washington D.C.,USA:IEEE Press,2016:1-8.

Please choose a citation manager

Content to export