• Laser & Optoelectronics Progress
  • Vol. 60, Issue 12, 1210013 (2023)
Xiangping Wu1,2,*, Qingqing Gao1, Shaowei Huang1, and Ke Wang1
Author Affiliations
  • 1College of Information Engineering, China Jiliang University, Hangzhou 310018, Zhejiang, China
  • 2Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province Hangzhou, China Jiliang University, 310018, Zhejiang, China
  • show less
    DOI: 10.3788/LOP221632 Cite this Article Set citation alerts
    Xiangping Wu, Qingqing Gao, Shaowei Huang, Ke Wang. Adaptive Retinex Image Defogging Algorithm Based on Depth-of-Field Information[J]. Laser & Optoelectronics Progress, 2023, 60(12): 1210013 Copy Citation Text show less
    Flow chart of dehazing algorithm
    Fig. 1. Flow chart of dehazing algorithm
    Network structure diagram of LPG
    Fig. 2. Network structure diagram of LPG
    Comparison of depth-of-field estimation. (a) Original drawings; (b) depth-of-field estimation map of color attenuation priori; (c) depth-of-field estimation map of BTS depth learning model
    Fig. 3. Comparison of depth-of-field estimation. (a) Original drawings; (b) depth-of-field estimation map of color attenuation priori; (c) depth-of-field estimation map of BTS depth learning model
    Linear fitting diagram
    Fig. 4. Linear fitting diagram
    Color unrecovered pseudo defog map
    Fig. 5. Color unrecovered pseudo defog map
    Bilinear interpolation
    Fig. 6. Bilinear interpolation
    Effect drawing of bilinear interpolation. (a) Before bilinear interpolation; (b) after bilinear interpolation
    Fig. 7. Effect drawing of bilinear interpolation. (a) Before bilinear interpolation; (b) after bilinear interpolation
    Comparison of dehazing effects of each algorithm. (a) Original drawings; (b) algorithm of reference [5]; (c) algorithm of reference [2]; (d) algorithm of reference [6]; (e) algorithm of reference [10]; (f) algorithm of reference [8]; (g) proposed algorithm
    Fig. 8. Comparison of dehazing effects of each algorithm. (a) Original drawings; (b) algorithm of reference [5]; (c) algorithm of reference [2]; (d) algorithm of reference [6]; (e) algorithm of reference [10]; (f) algorithm of reference [8]; (g) proposed algorithm
    Partial enlarged contrast diagrams. (a) Algorithm of reference [5]; (b) proposed algorithm
    Fig. 9. Partial enlarged contrast diagrams. (a) Algorithm of reference [5]; (b) proposed algorithm
    Partial enlarged contrast diagrams. (a) Algorithm of reference [6]; (b) proposed algorithm
    Fig. 10. Partial enlarged contrast diagrams. (a) Algorithm of reference [6]; (b) proposed algorithm
    ImageStandard deviationBrightness mean
    OriginalMSRCRAlgorithm of reference[6Algorithm of reference[10Algorithm of reference[8Proposed algorithmOriginalMSRCRAlgorithm of reference[6Algorithm of reference[10Algorithm of reference[8Proposed algorithm
    Village20.93423.29926.79724.39424.25827.901112.079139.91331.63850.04867.810106.871
    City51.79374.81160.85958.07455.77470.897125.364128.96999.56782.007115.867136.971
    Building57.37372.71551.10154.44460.60677.745108.797156.69970.25259.74687.254120.942
    Town53.51953.56244.58057.85961.84654.350125.194132.75773.04172.79294.869134.442
    Peak55.24956.64759.68060.22461.79060.249129.364128.85785.15690.58695.95796.980
    Table 1. Comparison of standard deviation and mean brightness of each algorithm's renderings
    ImageInformation entropyAverage gradient
    OriginalMSRCRAlgorithm of reference[6Algorithm of reference[10Algorithm of reference[8Proposed algorithmOriginalMSRCRAlgorithm of reference[6Algorithm of reference[10Algorithm of reference[8Proposed algorithm
    Village4.2475.1964.9444.2024.2105.281214.274447.548517.583549.089337.272491.281
    City5.1385.2485.3715.2115.2135.4502413.294124.394252.0784928.5863413.1714533.830
    Building4.9475.0215.1284.6924.8195.184454.610678.696681.916755.753690.4251738.238
    Town4.8224.8524.9474.9144.8685.173471.522871.047709.575936.947836.0291834.301
    Peak4.4644.6974.9565.1264.9325.187527.537571.859809.645909.864810.2381283.670
    Table 2. Comparison of standard deviation and mean brightness of each algorithm's renderings
    ImageStructural similarity
    MSRCRAlgorithm of reference[6Algorithm of reference[10Algorithm of reference[8Proposed algorithm
    106_Hazy0.7790.8770.8530.8730.881
    287_Hazy0.6460.8790.7340.7770.892
    Table 3. Comparison of structural similarity of renderings of various algorithms
    SSR
    PSNR19.2423.7529.2635.40
    Color correction
    Linear model
    Table 4. Influence of different modules on algorithm performance
    AlgorithmMSRCRAlgorithm of reference[6Algorithm of reference[10Algorithm of reference[8Proposed algorithm
    Time /s8.251.530.582.833.26
    Table 5. Comparison of demisting time of each algorithm
    Xiangping Wu, Qingqing Gao, Shaowei Huang, Ke Wang. Adaptive Retinex Image Defogging Algorithm Based on Depth-of-Field Information[J]. Laser & Optoelectronics Progress, 2023, 60(12): 1210013
    Download Citation