Enhanced Online Convolutional Neural Networks for Object Tracking

被引：0
|
作者：
Zhang, Dengzhuo [1 ]
Gao, Yun [1 ,2 ]
Zhou, Hao [1 ]
Li, Tianwen [3 ]
机构：
[1] Yunnan Univ, Sch Informat Sci & Engn, Kunming, Yunnan, Peoples R China
[2] Kunming Inst Phys, Kunming, Yunnan, Peoples R China
[3] Kunming Univ Sci & Technol, Fac Sci, Kunming, Yunnan, Peoples R China
来源：
TENTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2017) | 2018年 / 10696卷
基金：
中国国家自然科学基金; 中国博士后科学基金;
关键词：
object tracking; online convolution neural network; k-means plus; error back-propagation;
D O I：
10.1117/12.2310122
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In recent several years, object tracking based on convolution neural network has gained more and more attention. The initialization and update of convolution filters can directly affect the precision of object tracking effective. In this paper, a novel object tracking via an enhanced online convolution neural network without offline training is proposed, which initializes the convolution filters by a k-means++ algorithm and updates the filters by an error back-propagation. The comparative experiments of 7 trackers on 15 challenging sequences showed that our tracker can perform better than other trackers in terms of AUC and precision.
引用
收藏
页数：7
相关论文
共 50 条
  • [1] ONLINE MULTI-OBJECT TRACKING WITH CONVOLUTIONAL NEURAL NETWORKS
    Chen, Long
    Ai, Haizhou
    Shang, Chong
    Zhuang, Zijie
    Bai, Bo
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 645 - 649
  • [2] Online Tracking with Convolutional Neural Networks
    Liu, Xiaodong
    Zhou, Yue
    NEURAL INFORMATION PROCESSING (ICONIP 2017), PT III, 2017, 10636 : 208 - 216
  • [3] Attentional Convolutional Neural Networks for Object Tracking
    Kong, Xiangdong
    Cao, Xianbin
    2018 INTEGRATED COMMUNICATIONS, NAVIGATION, SURVEILLANCE CONFERENCE (ICNS), 2018,
  • [4] ATTENTIONAL CONVOLUTIONAL NEURAL NETWORKS FOR OBJECT TRACKING
    Kong, Xiangdong
    Zhang, Baochang
    Yue, Lei
    Xiao, Zehao
    2018 INTEGRATED COMMUNICATIONS, NAVIGATION, SURVEILLANCE CONFERENCE (ICNS), 2018,
  • [5] Object Tracking and Detection Using Convolutional Neural Networks
    Sujatha, C. N.
    Sahithi, P.
    Hamsini, R.
    Haripriya, M.
    PROCEEDINGS OF SECOND INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTER ENGINEERING AND COMMUNICATION SYSTEMS, ICACECS 2021, 2022, : 97 - 107
  • [6] Enhanced wavelet convolutional neural networks for visual tracking
    Guo, Qiang
    Cao, Xuefei
    Zou, Qinglong
    JOURNAL OF ELECTRONIC IMAGING, 2018, 27 (05)
  • [7] Deep convolutional neural networks for thermal infrared object tracking
    Liu, Qiao
    Lu, Xiaohuan
    He, Zhenyu
    Zhang, Chunkai
    Chen, Wen-Sheng
    KNOWLEDGE-BASED SYSTEMS, 2017, 134 : 189 - 198
  • [8] Object Tracking with Convolutional Neural Networks and Kernelized Correlation Filters
    Li, Dongxuan
    Chen, Wenjie
    2017 29TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC), 2017, : 1039 - 1044
  • [9] Moving object detection and tracking Using Convolutional Neural Networks
    Mane, Shraddha
    Mangale, Supriya
    PROCEEDINGS OF THE 2018 SECOND INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND CONTROL SYSTEMS (ICICCS), 2018, : 1809 - 1813
  • [10] Multi-Object Tracking with Quadruplet Convolutional Neural Networks
    Son, Jeany
    Baek, Mooyeol
    Cho, Minsu
    Han, Bohyung
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 3786 - 3795
12345