Confidence map based KCF object tracking algorithm

被引:2
|
作者
Wei, Baoguo [1 ]
Wang, Yufei [1 ]
He, Xingjian [1 ]
机构
[1] Northwestern Polytech Univ, Sch Elect Informat, Xian, Peoples R China
来源
PROCEEDINGS OF THE 2019 14TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA 2019) | 2019年
关键词
object tracking; confidence map; kernelized correlation filter; model update mechanism;
D O I
10.1109/iciea.2019.8834374
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Tracking with kernelized correlation filters (KCF) is an excellent object tracking algorithm, which is widely concerned. In KCF, each candidate patch in tracked region corresponds to a confidence ratio indicating the probability of containing the target, and the patch with the maximum confidence ratio is the output. In traditional KCF, its tracking performance decreases in complex scenes and the model is liable to he contaminated due to updated every frame. To overcome these limitations, we combine all available confidence ratios to form a confidence map, then by analyzing the confidence map, we infer the tracking scene and adopt different tracking strategies. For complex scenes, we dynamically improve KCF to enhance its tracking performance. In addition, we propose an innovative model update mechanism to reduce the computational complexity and model contamination. The experimental results show that compared with the conventional KCF algorithm, the proposed approach improves success rate and precision by 7% and 8% respectively.
引用
收藏
页码:2187 / 2192
页数:6
相关论文
共 50 条
  • [21] Saliency map for object tracking
    Zhang, Dongping
    Li, Wenting
    Sun, Min
    Yu, Haibin
    International Journal of Signal Processing, Image Processing and Pattern Recognition, 2015, 8 (10) : 233 - 240
  • [22] Midlevel cues mean shift visual tracking algorithm based on target-background saliency confidence map
    Zhengping Hu
    Ronglu Xie
    Meng Wang
    Zhe Sun
    Multimedia Tools and Applications, 2017, 76 : 21265 - 21280
  • [23] Object tracking algorithm based on deep feature
    Cheng X.
    Zhang Y.
    Liu Y.
    Cui J.
    Zhou L.
    Zhang, Yifeng (yfz@seu.edu.cn), 2017, Southeast University (47): : 1 - 5
  • [24] Midlevel cues mean shift visual tracking algorithm based on target-background saliency confidence map
    Hu, Zhengping
    Xie, Ronglu
    Wang, Meng
    Sun, Zhe
    MULTIMEDIA TOOLS AND APPLICATIONS, 2017, 76 (20) : 21265 - 21280
  • [25] An object tracking algorithm based on projective invariants
    Mei, Shuqi
    Zou, Wei
    Zhang, Huaixiang
    Yuan, Kui
    2006 IEEE INTERNATIONAL CONFERENCE ON INFORMATION ACQUISITION, VOLS 1 AND 2, CONFERENCE PROCEEDINGS, 2006, : 337 - 342
  • [26] Research of Object Tracking Algorithm Based on BRISK
    Guo Shixu
    Chen Jiaxin
    Peng Bo
    MODERN TECHNOLOGIES IN MATERIALS, MECHANICS AND INTELLIGENT SYSTEMS, 2014, 1049 : 1496 - 1501
  • [27] A Framework of Object Tracking Based on STC Algorithm
    Li, Qiuchen
    Li, Junbao
    Hu, Cong
    Pan, Jeng-Shyang
    PROCEEDINGS FIRST INTERNATIONAL CONFERENCE ON ELECTRONICS INSTRUMENTATION & INFORMATION SYSTEMS (EIIS 2017), 2017, : 809 - 813
  • [28] A Robust Object Tracking Algorithm Based on SURF
    Zhou Dan
    Hu Dong
    2013 INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING (WCSP 2013), 2013,
  • [29] A Target Tracking Method Based on KCF for Omnidirectional Vision
    Cai, Chengtao
    Liang, Xin
    Wang, Boyu
    Cui, Yujia
    Yan, Yongjie
    2018 37TH CHINESE CONTROL CONFERENCE (CCC), 2018, : 2674 - 2679
  • [30] Hyperspectral low altitude UAV target tracking algorithm based on deep learning and improved KCF
    Sun, Haodong
    Ma, Pengge
    Li, Zhenghao
    Ye, Zhaoyi
    Ma, Yueran
    FRONTIERS IN PHYSICS, 2024, 12