Underwater video enhancement using enhanced white balance adaptive algorithm and multithreading technique
Loading...
Date
2009-06
Authors
al-Ruwaili, Madallah Mukammi Munahi
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In underwater situations, there is a number of factors which lead to low
illumination, low contrast, and bluish color cast. These factors are light absorption,
scattering of light, and turbidity of water. Therefore, it is difficult to enhance
underwater images compared to land image. This study enhances the White Balance
Adaptive (WBA) algorithm to address the problem of underwater situations. The
WBA was parallelized for underwater images and videos. The enhanced sequential
WBA is based on two algorithms: Contrast Correction and White Balance. The
enhancement of Contrast Correction approach fully stretches underwater images and
the original pattern remains similar to the original histogram. The Enhanced WBA
algorithm removes the color cast based on statistical calculations. Enhancement
approach of correcting the affected image was done by applying three gain factors,
namely the red, green and blue gain factors. The proposed parallel algorithm is based
on data decomposition technique in which the image data is divided into sub sections
that can be processed simultaneously. Both of the proposed sequential and parallel
algorithms have been evaluated using the five well known methods namely:
Histogram, Edge Detection, Execution Time, Speed Up, and Efficiency. In addition,
the video processing was evaluated by comparison between the parallel algorithm,
the sequential algorithm, and the existing approach. Furthermore, Enhanced WBA
algorithms have performed well and the results are acceptable as compared to the
existing work.
Description
Keywords
The White Balance Adaptive (WBA) algorithm , to address the problem of underwater situations