An improved KCF tracking algorithm based on multi-feature and multi-scale

被引:1
|
作者
Wu, Wei [1 ,2 ]
Wang, Ding [1 ,2 ]
Luo, Xin [1 ,2 ]
Su, Yang [1 ,2 ]
Tian, Weiye [1 ,2 ]
机构
[1] Wuhan Univ Technol, Sch Informat Engn, Wuhan 430070, Hubei, Peoples R China
[2] Wuhan Univ Technol, Minist Educ, Key Lab Fiber Opt Sensing Technol & Informat Proc, Wuhan 430070, Hubei, Peoples R China
来源
MIPPR 2017: AUTOMATIC TARGET RECOGNITION AND NAVIGATION | 2018年 / 10608卷
关键词
visual tracking; kernel correlation filters; multi-feature integration; multi-scale transformation;
D O I
10.1117/12.2282345
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
The purpose of visual tracking is to associate the target object in a continuous video frame. In recent years, the method based on the kernel correlation filter has become the research hotspot. However, the algorithm still has some problems such as video capture equipment fast jitter, tracking scale transformation. In order to improve the ability of scale transformation and feature description, this paper has carried an innovative algorithm based on the multi feature fusion and multi-scale transform. The experimental results show that our method solves the problem that the target model update when is blocked or its scale transforms. The accuracy of the evaluation (OPE) is 77.0%, 75.4% and the success rate is 69.7%, 66.4% on the VOT and OTB datasets. Compared with the optimal one of the existing target-based tracking algorithms, the accuracy of the algorithm is improved by 6.7% and 6.3% respectively. The success rates are improved by 13.7% and 14.2% respectively.
引用
收藏
页数:7
相关论文
共 50 条
  • [1] An adaptive KCF tracking via multi-feature fusion
    Guo De-quan
    Peng Sheng
    Ling Sheng-gui
    Yang Hong-yu
    Liu Hong
    2017 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY AND VISUALIZATION (ICVRV 2017), 2017, : 255 - 260
  • [2] Research on improved multi-scale KCF target tracking algorithm based on features fusion and self-correction
    Chen Z.
    Liu W.
    High Technology Letters, 2022, 32 (04) : 337 - 350
  • [3] An improved UPF object tracking algorithm based on multi-feature fusion
    Li, Xiao-Xu
    Dai, Bin
    Cao, Jie
    Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University, 2014, 48 (10): : 1473 - 1478
  • [4] Target Detection and Tracking Algorithm based on the Improved Multi-feature Camshift
    Fang, Naihui
    Fu, Wei
    PROCEEDINGS OF THE 2014 INTERNATIONAL CONFERENCE ON MECHATRONICS, ELECTRONIC, INDUSTRIAL AND CONTROL ENGINEERING, 2014, 5 : 1569 - +
  • [5] Multi-Scale Multi-Feature Codebook-Based Background Subtraction
    Zaharescu, Andrei
    Jamieson, Michael
    2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCV WORKSHOPS), 2011,
  • [6] Multi-feature tracking algorithm based on compressed sensing
    Yu, Zhezhou, 1600, Binary Information Press (10):
  • [7] Improved DeepSORT Algorithm Based on Multi-Feature Fusion
    Liu, Haiying
    Pei, Yuncheng
    Bei, Qiancheng
    Deng, Lixia
    APPLIED SYSTEM INNOVATION, 2022, 5 (03)
  • [8] An Improved ORB Algorithm Based on Multi-feature Fusion
    Ma, Chaoqun
    Hu, Xiaoguang
    Fu, Li
    Zhang, Guofeng
    2018 IEEE 27TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE), 2018, : 729 - 734
  • [9] Accurate Retrieval of Multi-scale Clothing Images Based on Multi-feature Fusion
    Wang Z.-W.
    Pu Y.-Y.
    Wang X.
    Zhao Z.-P.
    Xu D.
    Qian W.-H.
    Jisuanji Xuebao/Chinese Journal of Computers, 2020, 43 (04): : 740 - 754
  • [10] An Optimized PatchMatch for multi-scale and multi-feature label fusion
    Giraud, Remi
    Vinh-Thong Ta
    Papadakis, Nicolas
    Manjon, Jose V.
    Collins, D. Louis
    Coupe, Pierrick
    NEUROIMAGE, 2016, 124 : 770 - 782