• Laser & Optoelectronics Progress
  • Vol. 59, Issue 17, 1733001 (2022)
Wei Song1, Xiaochen Liu1、*, Dongmei Huang1、2、**, Kelin Sun3, and Bing Zhang3
Author Affiliations
  • 1College of Information, Shanghai Ocean University, Shanghai 201306, China
  • 2Shanghai University of Electric Power, Shanghai 201306, China
  • 3Institute of Deep-Sea Science and Engineering, Chinese Academy of Sciences, Sanya 572000, Hainan , China
  • show less
    DOI: 10.3788/LOP202259.1733001 Cite this Article Set citation alerts
    Wei Song, Xiaochen Liu, Dongmei Huang, Kelin Sun, Bing Zhang. Construction of Video Quality Assessment Dataset for Deep-Sea Exploration[J]. Laser & Optoelectronics Progress, 2022, 59(17): 1733001 Copy Citation Text show less
    Flow chart of constructing the underwater video quality assessment dataset
    Fig. 1. Flow chart of constructing the underwater video quality assessment dataset
    Examples of five classes of contents about underwater videos. (a) Submarine rubbish; (b) submarine topography; (c) hydrothermal vents; (d) marine operation; (e) marine life
    Fig. 2. Examples of five classes of contents about underwater videos. (a) Submarine rubbish; (b) submarine topography; (c) hydrothermal vents; (d) marine operation; (e) marine life
    Original and Fusion enhanced underwater images. (a) Original image; (b) image enhanced with Fusion model
    Fig. 3. Original and Fusion enhanced underwater images. (a) Original image; (b) image enhanced with Fusion model
    Original and Ucolor enhanced underwater images.(a) Original image; (b) image enhanced with Ucolor model
    Fig. 4. Original and Ucolor enhanced underwater images.(a) Original image; (b) image enhanced with Ucolor model
    ROI area (inside the box) and non-ROI area (outside the box) of a single frame
    Fig. 5. ROI area (inside the box) and non-ROI area (outside the box) of a single frame
    Flow chart of subjective assessment of video quality
    Fig. 6. Flow chart of subjective assessment of video quality
    Subjective video quality assessment system. (a) Viewing interface; (b) assessment interface
    Fig. 7. Subjective video quality assessment system. (a) Viewing interface; (b) assessment interface
    Performance of underwater enhancement models in low light environment. (a) Original frame, MOS is 28.1; (b) enhanced by Fusion, MOS is 17.2; (c) enhanced by Ucolor, MOS is 20.9
    Fig. 8. Performance of underwater enhancement models in low light environment. (a) Original frame, MOS is 28.1; (b) enhanced by Fusion, MOS is 17.2; (c) enhanced by Ucolor, MOS is 20.9
    Performance of underwater enhancement models in color cast environment. (a) Original frame, MOS is 43.6; (b) enhanced by Fusion, MOS is 58.4; (c) enhanced by Ucolor, MOS is 50.4
    Fig. 9. Performance of underwater enhancement models in color cast environment. (a) Original frame, MOS is 43.6; (b) enhanced by Fusion, MOS is 58.4; (c) enhanced by Ucolor, MOS is 50.4
    Type of degradationParameterROINon-ROI
    Gaussian blurringKernel5×53×3
    Sigma31
    Gaussian noiseMean00
    STD118
    Table 1. Details of video quality degradation parameters
    MethodEnhancement modelDegradation model
    UcolorFusionROI_GBROI_GN
    Percentage of quality scores higher or lower than the original video /%3533-72-67
    Table 2. Subjective performance of video quality enhancement and degradation methods
    Classification of objective quality assessment modelModelCorrelation index
    PLCCSROCC
    Underwater sceneImageUCIQE220.32590.2293
    ImageUIQM230.30540.3272
    ImageGuo’s240.43100.3219
    VideoMoreno-Roldán’s90.34550.2590
    VideoSong’s60.51030.4936
    Terrestrial sceneImageBrisque250.39530.4239
    VideoVBliinds270.67350.6336
    VideoVIIDEO260.64230.6060
    Table 3. Performance comparison of different image/video quality assessment models on the dataset constructed in this paper
    Objective assessment modelPLCC/SROCC
    OursSong’s dataset6Moreno-Roldán’s dataset8
    Song’s60.51/0.490.84/0.83
    Moreno-Roldán’s90.35/0.260.80/0.76
    VIIDEO260.64/0.610.01/0.010.12/0.11
    Table 4. Results of video quality assessment models on different underwater video datasets
    Feature classFeature nameCorrelation
    Spatial domainUnderwater image colorfulness(UIQM)0.299**
    Underwater image contrast(UIQM)0.284**
    Natural image statisticsBrisque_1(Brisque)-0.369**
    Brisque_2,3,4,6,8,10,12,14,16,18(Brisque)-0.230**~-0.312**
    NIQE_4(VBliinds)0.260**
    NIQE_5(VBliinds)-0.216**
    NIQE_8(VBliinds)0.247**
    NIQE_16(VBliinds)0.292**
    NIQE_22(VBliinds)0.216**
    Frequency domainDC_variation(VBliinds)0.430**
    MotionGlobal motion(VBliinds)-0.249**
    Table 5. Correlation analysis of video quality characteristics
    Wei Song, Xiaochen Liu, Dongmei Huang, Kelin Sun, Bing Zhang. Construction of Video Quality Assessment Dataset for Deep-Sea Exploration[J]. Laser & Optoelectronics Progress, 2022, 59(17): 1733001
    Download Citation