• Laser & Optoelectronics Progress
  • Vol. 57, Issue 18, 181014 (2020)
Chen Qu1、* and Duyan Bi2
Author Affiliations
  • 1School of Management, Xi'an University of Finance and Economics, Xi'an, Shaanxi 710100, China
  • 2Institute of Aeronautics and Astronautics, Air Force Engineering University, Xi'an, Shaanxi 710038, China
  • show less
    DOI: 10.3788/LOP57.181014 Cite this Article Set citation alerts
    Chen Qu, Duyan Bi. Haze Image Restoration Based on Multi-Prior Constraints[J]. Laser & Optoelectronics Progress, 2020, 57(18): 181014 Copy Citation Text show less
    Atmospheric scattering model
    Fig. 1. Atmospheric scattering model
    Analysis results of color attenuation prior of “distant mountain” and “red building”. (a) Haze images; (b) black and white difference images; (c) relationship curves between brightness and saturation difference and scene depth
    Fig. 2. Analysis results of color attenuation prior of “distant mountain” and “red building”. (a) Haze images; (b) black and white difference images; (c) relationship curves between brightness and saturation difference and scene depth
    Different algorithms process “distant mountain”, “road” and “building” smog images and corresponding visible edges. (a)(b) Input haze images; (c)(d) Ref. [5]; (e)(f) proposed algorithm
    Fig. 3. Different algorithms process “distant mountain”, “road” and “building” smog images and corresponding visible edges. (a)(b) Input haze images; (c)(d) Ref. [5]; (e)(f) proposed algorithm
    Different algorithms process “wheatgrass”, “hill” and “orange” haze images and corresponding visible edges. (a)(b) Input haze images; (c)(d) Ref. [12]; (e)(f) proposed algorithm
    Fig. 4. Different algorithms process “wheatgrass”, “hill” and “orange” haze images and corresponding visible edges. (a)(b) Input haze images; (c)(d) Ref. [12]; (e)(f) proposed algorithm
    Different algorithms process “street”, “forest” and “village” smog images and corresponding visible edges. (a)(b) Input haze images; (c)(d) Ref. [13]; (e)(f) proposed algorithm
    Fig. 5. Different algorithms process “street”, “forest” and “village” smog images and corresponding visible edges. (a)(b) Input haze images; (c)(d) Ref. [13]; (e)(f) proposed algorithm
    Different algorithms process “goose”, “small building” and “mountain forest” smog images and corresponding visible edges. (a)(b) Input haze images; (c)(d) Ref. [8]; (e)(f) proposed algorithm
    Fig. 6. Different algorithms process “goose”, “small building” and “mountain forest” smog images and corresponding visible edges. (a)(b) Input haze images; (c)(d) Ref. [8]; (e)(f) proposed algorithm
    Fig.3VDIHR
    Ref. [5]ProposedalgorithmRef. [5]Proposedalgorithm
    Distantmountain0.43760.58320.68170.8673
    Road0.33910.69970.45380.7261
    Building0.52480.66130.62540.8392
    Table 1. Comparison of VDI and HR in Fig. 3 with different algorithms
    Fig.4VDIHR
    Ref. [12]ProposedalgorithmRef. [12]Proposedalgorithm
    Wheatgrass0.31940.65820.58330.7761
    Hill0.52880.79170.67020.8714
    Orange0.45700.67460.60910.8418
    Table 2. Comparison of VDI and HR in Fig. 4 with different algorithms
    Fig.5VDIHR
    Ref. [13]ProposedalgorithmRef. [13]Proposedalgorithm
    Street0.42770.73010.63750.8399
    Forest0.45910.62280.60270.7924
    Village0.43700.64190.65180.9067
    Table 3. Comparison of VDI and HR in Fig. 5 with different algorithms
    Fig.6VDIHR
    Ref. [8]ProposedalgorithmRef. [8]Proposedalgorithm
    Goose0.41360.68130.51950.7367
    Smallbuilding0.52880.72910.68300.8166
    Mountainforest0.49300.62050.47290.7804
    Table 4. Comparison of VDI and HR in Fig. 6 with different algorithms
    Chen Qu, Duyan Bi. Haze Image Restoration Based on Multi-Prior Constraints[J]. Laser & Optoelectronics Progress, 2020, 57(18): 181014
    Download Citation