• Acta Optica Sinica
  • Vol. 38, Issue 12, 1210001 (2018)
Aiping Yang*, Haixin Wang*, Jinbin Wang, Meiqi Zhao, and Liyu Lu
Author Affiliations
  • School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
  • show less
    DOI: 10.3788/AOS201838.1210001 Cite this Article Set citation alerts
    Aiping Yang, Haixin Wang, Jinbin Wang, Meiqi Zhao, Liyu Lu. Image Dehazing Based on Transmission Fusion and Multi-Guided Filtering[J]. Acta Optica Sinica, 2018, 38(12): 1210001 Copy Citation Text show less
    Flow chart of the proposed algorithm
    Fig. 1. Flow chart of the proposed algorithm
    Image decomposition
    Fig. 2. Image decomposition
    Block effects and halo effects. (a) Original image; (b) dark channel priors estimate transmittance; (c) restored image
    Fig. 3. Block effects and halo effects. (a) Original image; (b) dark channel priors estimate transmittance; (c) restored image
    Comparison of point transmission map. (a) Transmission estimated by pixel-based dark color; (b) result of Ref. [18]; (c) transmission estimated by proposed method; (d) dehazing result by proposed method
    Fig. 4. Comparison of point transmission map. (a) Transmission estimated by pixel-based dark color; (b) result of Ref. [18]; (c) transmission estimated by proposed method; (d) dehazing result by proposed method
    Flow chart of transmission fusion
    Fig. 5. Flow chart of transmission fusion
    Structure of decision image
    Fig. 6. Structure of decision image
    Hazy images and their corresponding decision images. (a)(d) Original images; (b)(e) histograms of decision images; (c)(f) decision images
    Fig. 7. Hazy images and their corresponding decision images. (a)(d) Original images; (b)(e) histograms of decision images; (c)(f) decision images
    Hazy image and its corresponding decision value of 0.1% pixel for the dark channel. (a)(c) Original images; (b)(d) histograms of dark channel decision image
    Fig. 8. Hazy image and its corresponding decision value of 0.1% pixel for the dark channel. (a)(c) Original images; (b)(d) histograms of dark channel decision image
    Transmission optimization results with different filtering radius
    Fig. 9. Transmission optimization results with different filtering radius
    Filtering with the original image as the guided image
    Fig. 10. Filtering with the original image as the guided image
    Processes of multi-guided filtering
    Fig. 11. Processes of multi-guided filtering
    Comparison results. (a) Original images; (b) method in Ref. [18]; (c) proposed method
    Fig. 12. Comparison results. (a) Original images; (b) method in Ref. [18]; (c) proposed method
    Comparison results. (a) Original images; (b) method in Ref. [21]; (c) proposed method
    Fig. 13. Comparison results. (a) Original images; (b) method in Ref. [21]; (c) proposed method
    Comparison results. (a) Original images; (b) method in Ref. [22]; (c) proposed method
    Fig. 14. Comparison results. (a) Original images; (b) method in Ref. [22]; (c) proposed method
    Comparison results of proposed method and traditional methods. (a) Original images; (b) method in Ref. [11]; (c) method in Ref. [6]; (d) method in Ref. [7]; (e) proposed method
    Fig. 15. Comparison results of proposed method and traditional methods. (a) Original images; (b) method in Ref. [11]; (c) method in Ref. [6]; (d) method in Ref. [7]; (e) proposed method
    Comparisonof results of proposed method and deep learning methods. (a) Original images; (b) method in Ref. [13]; (c) method in Ref. [12]; (d) proposed method
    Fig. 16. Comparisonof results of proposed method and deep learning methods. (a) Original images; (b) method in Ref. [13]; (c) method in Ref. [12]; (d) proposed method
    AlgorithmImage size /(pixel×pixel)Time /s
    Ref. [8]640×4800.2143
    Ref. [11]640×4800.9127
    Proposed640×4800.1653
    Table 1. Time of the process of transmission optimization from different algorithms
    IndexRef. [18]ProposedRef. [21]ProposedRef. [22]Proposed
    e0.060.220.270.340.820.89
    0.200.100.060.150.080.09
    -0.160.050.050.080.590.59
    r1.432.202.342.252.653.27
    3.692.891.292.451.332.09
    1.273.061.101.811.533.05
    Table 2. Objective evaluation index of different fusion algorithms
    Aiping Yang, Haixin Wang, Jinbin Wang, Meiqi Zhao, Liyu Lu. Image Dehazing Based on Transmission Fusion and Multi-Guided Filtering[J]. Acta Optica Sinica, 2018, 38(12): 1210001
    Download Citation