• Laser & Optoelectronics Progress
  • Vol. 56, Issue 2, 021502 (2019)
Jianfeng Yang* and Jianpeng Zhang
Author Affiliations
  • School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, Gansu 730070, China
  • show less
    DOI: 10.3788/LOP56.021502 Cite this Article Set citation alerts
    Jianfeng Yang, Jianpeng Zhang. Long Time Target Tracking Based on Kernel Correlation Filtering[J]. Laser & Optoelectronics Progress, 2019, 56(2): 021502 Copy Citation Text show less
    Schematic of sub-block MS tracking algorithm
    Fig. 1. Schematic of sub-block MS tracking algorithm
    Precision curves and success rate curves of four trackers. (a) Precision; (b) success rate
    Fig. 2. Precision curves and success rate curves of four trackers. (a) Precision; (b) success rate
    Precision curves and success rate curves of four contrast algorithms under occlusion condition. (a) Precision; (b) success rate
    Fig. 3. Precision curves and success rate curves of four contrast algorithms under occlusion condition. (a) Precision; (b) success rate
    Pictures of tracking effect
    Fig. 4. Pictures of tracking effect
    VideoFrameTarget size /(pixel×pixel)Influence factor
    Car scale25226×42Scale variation, occlusion
    Crossing12050×17Illumination variation, background clutter
    David3252131×35Occlusion, background clutter, rotation
    Lemming1336103×61Occlusion, Scale variation, rotation
    Jogging307101×25Occlusion, background clutter
    Subway17551×19Occlusion, rotation
    Walking41279×24Scale variation, deformation
    Warlking2500115×31Scale variation, occlusion, low resolution
    Table 1. Video sequence
    AlgorithmCLEVORFrame rate /(frame·s-1)
    CSK80.780.389186.2
    KCF35.320.499233.2
    CN62.780.401141.8
    Ours30.020.58946.08
    Table 2. Performance comparison of different tracking algorithms
    Jianfeng Yang, Jianpeng Zhang. Long Time Target Tracking Based on Kernel Correlation Filtering[J]. Laser & Optoelectronics Progress, 2019, 56(2): 021502
    Download Citation