Underwater image restoration method based on secondary guided transmission image
An underwater image and transmission map technology, applied in the field of image restoration, can solve the problem of large transmission map estimation, and achieve the effect of improving contrast, restoring color and details
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach
[0059] In a preferred embodiment, the underwater imaging model formula in the step S05 is:
[0060] I c (x)=J c (x)t c (x)+A c (1-t c (x)), c ∈ {r, g, b};
[0061] Among them, I c (x) represents the original image, J c (x)tc(x) represents the direct component, A c (1-tc(x)) represents the background light scattering component, J c (x) represents the restored image, A c Indicates the background light intensity, t c (x) represents the refinement transmission map;
[0062] According to the background light obtained in the step S02 and the transmission map obtained in the step S04, combined with the underwater imaging model to perform inversion, the restoration formula is:
[0063]
[0064] Among them, α∈{R,G,B}, in order to avoid overflow caused by too low transmission map, add a lower limit t to t 0 , t 0 The value is 0.1. Since the restored image cannot guarantee that the value is in [0,1], the minimum-maximum normalized intensity value is used to adjust its va...
Embodiment
[0070] Such as figure 2 As shown, the present invention provides an experimental effect diagram after various algorithms restoration processing of underwater rocks with other algorithms. in diagram 2-1 represents the original image, Figure 2-2 Denotes the result graph of He; Figure 2-3 Indicates the result graph of Drews; Figure 2-4 Indicates the result plot of Iqbal; figure 2 -5 indicates Peng's result graph; figure 2 -6 represents the result graph of the method of the present invention. It can be seen from the experimental effect diagram that these five algorithms can restore the image to a certain extent, and improve the visibility and local detail effect of the image. The He and Drews algorithm has a color cast problem and poor visibility. Peng's algorithm removes fog from the original image, but the visibility is not good enough. The Iqbal algorithm enhances the visibility and color to a certain extent, but the method of the present invention has clear visi...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More