Chinese Optics, Volume. 15, Issue 4, 689(2022)
Brightness correction and color restoration of seabed image obtained by active optical detection
Fig. 1. Relative distribution of illuminance under vertical illumination of the point light source . (a) Schematic of vertical illumination of the ideal point light source and (b) schematic of light intensity attenuation
Fig. 3. Underwater optical image of a uniform seafloor illuminated by the point light source
Fig. 4. Each channel of the reference image and their brightness fitting surface (a)−(c) red, green, blue channels of the reference image; (d)−(f) 3D top view of the red, green and blue channels; (g)−(i) fitting surface of the red, green, blue channels
Fig. 5. Individual brightness compensation for each channel of the reference image (a)−(c) Degree of compensation of the red, green and blue channels; (d)−(f) compensated red, green and blue single channel images
Fig. 6. The compensation process of the image in the same batch with reference image correction parameters. (a)−(c) Original gray images of the red, green and blue channels, (d)−(f) compensated images of the three channels
Fig. 7. Comparison of image enhancement with different pre-processing methods. (a) Pre-compensation image; (b)−(f) compensated results with Gray world, the proposed pre-processing method, MSR, Gray world + MSR, and the proposed pre-processing method + MSR methods
Fig. 8. Comparison of correction results of the underwater image processed by different algorithms. (a) MSR; (b) CLAHE; (c) RCP; (d) RWCGC; (e) UWCNN; (f) The proposed method
Fig. 9. Comparison of underwater image enhancement processed by different algorithms. (a) Original images; (b)−(g) the results obtained by MSR, CLAHE, RCP, RWCGC, UWCNN and the proposed method
Table 1. Quartic polynomial fitting parameters of the gray surface of each channel of the reference image
View tableView in ArticleTable 1. Quartic polynomial fitting parameters of the gray surface of each channel of the reference image
参数 R通道 G通道 B通道 a00 19.25 46.32 50.18 a10 −0.1006 0.4208 0.4696 a01 −0.1152 0.3904 0.4299 a20 1.005×10−3 −4.915×10−4 −7.192×10−4 a11 1.038×10−3 −6.395×10−4 −8.548×10−4 a02 1.002×10−3 −4.785×10−4 −6.328×10−4 a30 −2.241×10−6 1.353×10−7 6.774×10−7 a21 −1.584×10−6 −2.121×10−7 −1.141×10−7 a12 −7.252×10−7 2.581×10−6 3.145×10−6 a03 −2.75×10−6 −8.219×10−7 −5.752×10−7 a40 1.391×10−9 −8.548×10−10 −1.382×10−9 a31 3.485×10−10 3.321×10−9 4.136×10−9 a22 2.072×10−9 −4.899×10−9 −6.476×10−9 a13 −1.332×10−9 4.571×10−10 1.053×10−9 a04 2.382×10−9 3.993×10−10 7.139×10−11
Table 2. Objective image quality evaluation results of the reference image and images processed by different algorithms
View tableView in ArticleTable 2. Objective image quality evaluation results of the reference image and images processed by different algorithms
指标 参考图像 MSR CLAHE RCP RWCGC UWCNN Ours 注：加粗字体为每行最优值。 UIQM 0.9322 3.809 2.3193 3.3535 3.1508 1.4238 4.0546 UCIQE 20.3988 24.9813 25.6173 24.0433 28.7847 21.4546 28.2705
Table 3. Objective image quality evaluation results of the first column of Fig. 9 processed by different algorithms
View tableView in ArticleTable 3. Objective image quality evaluation results of the first column of Fig. 9 processed by different algorithms
指标 图9 第一列原图MSR CLAHE RCP RWCGC UWCNN Ours 注：加粗字体为每行最优值。 UIQM 1.0147 3.8557 2.9908 2.6969 3.6444 3.0211 4.5062 UCIQE 18.2575 28.0713 24.3802 22.4397 29.3778 21.9017 29.8468
Table 4. Objective image quality evaluation indexes of the second column of Fig. 9 processed by different algorithms
View tableView in ArticleTable 4. Objective image quality evaluation indexes of the second column of Fig. 9 processed by different algorithms
指标 图9 第二列原图MSR CLAHE RCP RWCGC UWCNN Ours 注：加粗字体为每行最优值 UIQM 1.0147 3.8557 2.9908 2.6969 3.6444 3.0211 4.5583 UCIQE 20.5561 27.6709 27.5439 24.2877 29.0778 20.9523 29.5887
Table 5. Objective image quality evaluation indexes of the third column of Fig. 9 processed by different algorithms
View tableView in ArticleTable 5. Objective image quality evaluation indexes of the third column of Fig. 9 processed by different algorithms
图9 第三列原图MSR CLAHE RCP RWCGC UWCNN Ours 注：加粗字体为每行最优值 UIQM 0.6739 3.7142 2.8359 2.4611 3.12146 2.6183 4.3095 UCIQE 20.0312 28.1392 25.5831 23.8943 29 . 099622.8868 29.1635
Get Citation
Copy Citation Text
Rong-tao LIU, Jia-hang LIU. Brightness correction and color restoration of seabed image obtained by active optical detection[J]. Chinese Optics, 2022, 15(4): 689
Category: Original Article
Received: Dec. 6, 2021
Accepted: --
Published Online: Sep. 6, 2022
The Author Email:
