Acta Optica Sinica, Volume. 45, Issue 9, 0910003(2025)

Hyperspectral Target Tracking Based on Environmental Residual-Aware Multi-Regularized Correlation Filter

Xiaoqing Tian1,2、*, Bao Liu1,2, Qiang Guo1,2, and Hongguang Pan1,2
Author Affiliations
  • 1Xi’an Key Laboratory of Electrical Equipment Status Monitoring and Power Supply Safety, Xi’an 710054, Shaanxi , China
  • 2School of Electrical and Control Engineering, Xi’an University of Science and Technology, Xi’an 710054, Shaanxi , China
  • show less
    Figures & Tables(13)
    Overall flowchart of the proposed algorithm
    Feature fusion based on false-color/three-band spectral images. (a) Original false-color image of frame 2 in L_car2 sequence; (b) feature extracted from three-band spectral image; (c) feature extracted from false-color image; (d) false-color/spectral image feature fusion
    Performance comparisons of 5 tracking algorithms on HOTC2024. (a) Success rate plots; (b) precision plots
    Performance comparisons of 5 tracking algorithms on the fast motion challenge of HOTC2024. (a) Success rate plots; (b) precision plots
    Performance comparisons of 5 tracking algorithms on the scale variation challenge of HOTC2024. (a) Success rate plots; (b) precision plots
    Performance comparisons of 5 tracking algorithms on IMEC25. (a) Success rate plots; (b) precision plots
    Performance comparisons of 5 tracking algorithms on the fast motion challenge of IMEC25. (a) Success rate plots; (b) precision plots
    Performance comparisons of 5 tracking algorithms on the scale variation challenge of IMEC25. (a) Success rate plots; (b) precision plots
    Qualitative comparison results of three groups of videos in the HOTC2024 test sequence. (a) Droneshow2; (b) L_car2; (c) Officechair2
    Two failure cases of the proposed algorithm in two sequences of HOTC2024. (a) pool2; (b) S_soccer4
    • Table 1. FPS comparisons of 5 tracking algorithms on HOTC2024 (highlight the optimal value in bold)

      View table

      Table 1. FPS comparisons of 5 tracking algorithms on HOTC2024 (highlight the optimal value in bold)

      AlgorithmOursMHTTSCFWDeepKCFMRCF
      FPS8.825.269.0531.4013.68
    • Table 2. Precision and success rate of ablation experiments on HOTC2024 (highlight the optimal value in bold)

      View table

      Table 2. Precision and success rate of ablation experiments on HOTC2024 (highlight the optimal value in bold)

      AlgorithmMRCFMRCF+ERAMRCF+FCOurs
      Precision /%14.2450.4052.2254.30
      Success rate /%9.4436.1237.0937.87
    • Table 3. Precision and success rate of ablation experiments on IMEC25 (highlight the optimal value in bold)

      View table

      Table 3. Precision and success rate of ablation experiments on IMEC25 (highlight the optimal value in bold)

      AlgorithmMRCFMRCF+ERAMRCF+FCOurs
      Precision /%50.1379.5049.4881.83
      Success rate /%34.1659.3131.8561.17
    Tools

    Get Citation

    Copy Citation Text

    Xiaoqing Tian, Bao Liu, Qiang Guo, Hongguang Pan. Hyperspectral Target Tracking Based on Environmental Residual-Aware Multi-Regularized Correlation Filter[J]. Acta Optica Sinica, 2025, 45(9): 0910003

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: Dec. 24, 2024

    Accepted: Mar. 10, 2025

    Published Online: May. 16, 2025

    The Author Email: Xiaoqing Tian (tianxiaoqing2017@xust.edu.cn)

    DOI:10.3788/AOS241923

    CSTR:32393.14.AOS241923

    Topics