• Infrared and Laser Engineering
  • Vol. 51, Issue 4, 20210417 (2022)
Yaping Wang1, [in Chinese]1, and Baohua Zhang1、2、*
Author Affiliations
  • 1College of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, China
  • 2Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing, Inner Mongolia University of Science and Technology, Baotou 014010, China
  • show less
    DOI: 10.3788/IRLA20210417 Cite this Article
    Yaping Wang, [in Chinese], Baohua Zhang. Infrared small target detection based on dehazing enhancement and tensor recovery[J]. Infrared and Laser Engineering, 2022, 51(4): 20210417 Copy Citation Text show less
    Tensor singular value decomposition
    Fig. 1. Tensor singular value decomposition
    Infrared small target images. (a)-(c) Real scenes of sky background with thick cloud; (d)-(f) Real scenes of sky background with buildings and other complex occluders
    Fig. 2. Infrared small target images. (a)-(c) Real scenes of sky background with thick cloud; (d)-(f) Real scenes of sky background with buildings and other complex occluders
    Construction of patch-tensor model (Left: Original infrared image; Right: Constructed patch-tensor)
    Fig. 3. Construction of patch-tensor model (Left: Original infrared image; Right: Constructed patch-tensor)
    Nonlocal self-correlation property of unfolding matrices. (a) Infrared images; (b)-(d) Singular value curves of mode-1, mode-2, and mode-3 unfolding matrices
    Fig. 4. Nonlocal self-correlation property of unfolding matrices. (a) Infrared images; (b)-(d) Singular value curves of mode-1, mode-2, and mode-3 unfolding matrices
    Contrast results of dehazing enhancement in different scenes. (a) Seq.1; (b) Seq.2; (c) Seq.3; (4) Seq.4
    Fig. 5. Contrast results of dehazing enhancement in different scenes. (a) Seq.1; (b) Seq.2; (c) Seq.3; (4) Seq.4
    Detection results of proposed algorithm. (a) Original infrared images; (b) Input original images with global 3D surf plot; (c) Mark the detection result of the target with a rectangular box; (d) Local 3D surf plot of target
    Fig. 6. Detection results of proposed algorithm. (a) Original infrared images; (b) Input original images with global 3D surf plot; (c) Mark the detection result of the target with a rectangular box; (d) Local 3D surf plot of target
    Detection results of the different approaches to 4 sequences. (a) Original infrared images; (b) Top-Hat; (c) LoG; (d) LCM; (e) MPCM; (f) IPI; (g) PSTNN; (h) Proposed algorithm
    Fig. 7. Detection results of the different approaches to 4 sequences. (a) Original infrared images; (b) Top-Hat; (c) LoG; (d) LCM; (e) MPCM; (f) IPI; (g) PSTNN; (h) Proposed algorithm
    AlgorithmsFrame1Frame2Frame3Frame4
    SCRGBSFSCRGBSFSCRGBSFSCRGBSF
    Top-Hat1.3522.5876.533.981.1130.060.01519.51
    LoG7.9020.1746.7861.5664.322.230.1327.88
    LCM0.8740.6332.8510.7310.5871.341.0591.13
    MPCM2.2160.1540.0213.30346.523.850.019
    IPI101.4134.189.651.781.5814.40.02317.2
    PSTNN998.41158.65132.8598.5213.7743.3233.2
    Proposed1297.921405.38146.7733.2330.655.635.7
    Table 1. SCRG and BSF of different algorithms in different infrared image sequences
    Yaping Wang, [in Chinese], Baohua Zhang. Infrared small target detection based on dehazing enhancement and tensor recovery[J]. Infrared and Laser Engineering, 2022, 51(4): 20210417
    Download Citation