A Siamese Network for real-time object tracking on CPU

被引:2
作者
Xing, Daitao [1 ]
Evangeliou, Nikolaos [2 ]
Tsoukalas, Athanasios [2 ]
Tzes, Anthony [3 ]
机构
[1] NYU, New York, NY 10003 USA
[2] New York Univ Abu Dhabi, Abu Dhabi, U Arab Emirates
[3] New York Univ Abu Dhabi, Ctr Artificial Intelligence & Robot, Abu Dhabi, U Arab Emirates
关键词
Object tracking; Reduced complexity; Mobile devices; Siamese Network;
D O I
10.1016/j.simpa.2022.100266
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Visual object tracking methods depend upon deep networks that can hardly meet real-time processing requirements on mobile platforms with limited computing resources. In this work, we propose a real-time object tracking framework by enhancing a lightweight feature pyramid network with Transformer architecture to construct a robust target-specific appearance model efficiently. We further introduce the pooling attention module to avoid the computation and memory intensity while fusing pyramid features with the Transformer. The optimized tracker operates over 45 Hz on a single CPU, allowing researchers to deploy it on any mobile device with limited power resources.
引用
收藏
页数:4
相关论文
共 50 条
  • [41] Multi-level prediction Siamese network for real-time UAV visual tracking
    Zhu, Mu
    Zhang, Hui
    Zhang, Jing
    Zhuo, Li
    IMAGE AND VISION COMPUTING, 2020, 103 (103)
  • [42] Combined Kalman Filter and Multifeature Fusion Siamese Network for Real-Time Visual Tracking
    Zhou, Lijun
    Zhang, Jianlin
    SENSORS, 2019, 19 (09)
  • [43] Siamese Dense Pixel-Level Fusion Network for Real-Time UAV Tracking
    Huang, Zhenyu
    Li, Gun
    Sun, Xudong
    Chen, Yong
    Sun, Jie
    Ni, Zhangsong
    Yang, Yang
    CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 76 (03): : 3219 - 3238
  • [44] IoU-guided Siamese region proposal network for real-time visual tracking
    Zhou, Lifang
    He, Yu
    Li, Weisheng
    Mi, Jianxun
    Lei, Bangjun
    NEUROCOMPUTING, 2021, 462 : 544 - 554
  • [45] A Learning Frequency-Aware Feature Siamese Network for Real-Time Visual Tracking
    Yang, Yuxiang
    Xing, Weiwei
    Zhang, Shunli
    Yu, Qi
    Guo, Xiaoyu
    Guo, Min
    ELECTRONICS, 2020, 9 (05)
  • [46] Siamese adversarial network for object tracking
    Kim, H. -I.
    Park, R. -H.
    ELECTRONICS LETTERS, 2019, 55 (02) : 88 - +
  • [47] Real-Time Generic Object Tracking via Recurrent Regression Network
    Chen, Rui
    Tong, Ying
    Liang, Ruiyu
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2020, E103D (03) : 602 - 611
  • [48] Real-Time Object Tracking with YOLOv5 and Recurrent Network
    Mohammed, Al Ameri
    Memon, Qurban
    2024 7TH INTERNATIONAL CONFERENCE ON ELECTRONICS, COMMUNICATIONS, AND CONTROL ENGINEERING, ICECC 2024, 2024, : 28 - 32
  • [49] Alpha Divergence based Siamese Network for Object Tracking
    Wang, Zhan
    Wang, Kai
    Wang, Yanwei
    2021 IEEE INTL CONF ON DEPENDABLE, AUTONOMIC AND SECURE COMPUTING, INTL CONF ON PERVASIVE INTELLIGENCE AND COMPUTING, INTL CONF ON CLOUD AND BIG DATA COMPUTING, INTL CONF ON CYBER SCIENCE AND TECHNOLOGY CONGRESS DASC/PICOM/CBDCOM/CYBERSCITECH 2021, 2021, : 751 - 758
  • [50] Learning to Match Using Siamese Network for Object Tracking
    Li, Chaopeng
    Lu, Hong
    Jiao, Jian
    Zhang, Wenqiang
    ADVANCES IN MULTIMEDIA INFORMATION PROCESSING, PT III, 2018, 11166 : 719 - 729