End-to-end deep metric network for visual tracking

被引:0
|
作者
Shengjing Tian
Shuwei Shen
Guoqiang Tian
Xiuping Liu
Baocai Yin
机构
[1] Dalian University of Technology,School of Mathematical Sciences
[2] Dalian University of Technology,Faculty of Electronic Information and Electrical Engineering
来源
The Visual Computer | 2020年 / 36卷
关键词
Metric learning; Visual tracking; Deep neural networks; One-shot learning;
D O I
暂无
中图分类号
学科分类号
摘要
In this paper, we propose an end-to-end deep metric network (DMN) for visual tracking, where any target can be accurately tracked given only a bounding box of the first frame. Our main motivation is to make the network learn to learn a deep distance metric by following the philosophy of one-shot learning. Instead of utilizing a hand-crafted distance metric like Euclidean distance, our DMN focuses on providing a learnable metric, which is more robust to appearance variations. Furthermore, we are the first to properly combine mean square errors and contrastive loss into a joint loss function for back-propagation. During online tracking, DMN firstly applies our instance initialization for obtaining sequence-specific information and then straightforwardly tracks the target without the help of box refinement, occlusion detection and online updating. The final tracking score considers both our DMN scalar output and the constrain of motion smoothness. Ablation analyses are carried out to validate the effectiveness of our proposed method. And experiments on the prevalent benchmarks show that our method can achieve a competitive performance when compared with some representative trackers, especially those existing metric learning-based algorithms.
引用
收藏
页码:1219 / 1232
页数:13
相关论文
共 50 条
  • [31] An End-to-End Robotic Visual Localization Algorithm Based on Deep Learning
    Chen, Niansheng
    Wang, Hongcheng
    Fan, Guangyu
    Yang, Dingyu
    Rao, Lei
    JOURNAL OF SENSORS, 2023, 2023
  • [32] Enhancing continuous control of mobile robots for end-to-end visual active tracking
    Devo, Alessandro
    Dionigi, Alberto
    Costante, Gabriele
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2021, 142
  • [33] Hierarchical convolutional features for end-to-end representation-based visual tracking
    Suguo Zhu
    Zhenying Fang
    Fei Gao
    Machine Vision and Applications, 2018, 29 : 955 - 963
  • [34] Hierarchical convolutional features for end-to-end representation-based visual tracking
    Zhu, Suguo
    Fang, Zhenying
    Gao, Fei
    MACHINE VISION AND APPLICATIONS, 2018, 29 (06) : 955 - 963
  • [35] Tracking Counterfeit Cryptocurrency End-to-end
    Gao, Bingyu
    Wang, Haoyu
    Xia, Pengcheng
    Wu, Siwei
    Zhou, Yajin
    Luo, Xiapu
    Tyson, Gareth
    PROCEEDINGS OF THE ACM ON MEASUREMENT AND ANALYSIS OF COMPUTING SYSTEMS, 2020, 4 (03)
  • [36] An End-to-end Network for Monocular Visual Odometry Based on Image Sequence
    Yao, Mingwei
    Quan, Hongyan
    2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [37] AUV Position Tracking Control Using End-to-End Deep Reinforcement Learning
    Carlucho, Ignacio
    De Paula, Mariano
    Wang, Sen
    Menna, Bruno V.
    Petillot, Yvan R.
    Acosta, Gerardo G.
    OCEANS 2018 MTS/IEEE CHARLESTON, 2018,
  • [38] DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration
    Lu, Weixin
    Wan, Guowei
    Zhou, Yao
    Fu, Xiangyu
    Yuan, Pengfei
    Song, Shiyu
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 12 - 21
  • [39] End-to-End Deep Neural Network for Illumination Consistency and Global Illumination
    Huang Jingtao
    Komuro, Takashi
    ADVANCES IN VISUAL COMPUTING, ISVC 2022, PT I, 2022, 13598 : 392 - 403
  • [40] DeepChess :End-to-End Deep Neural Network for Automatic Learning in Chess
    David, Omid E.
    Netanyahu, Nathan S.
    Wolf, Lior
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II, 2016, 9887 : 88 - 96