Underwater Video Enhancement Using Enhanced Integra Ted Color Model Algorithm And Multithreading Technique
Loading...
Date
2009-06
Authors
Neima, Hikmat z
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Aquatic studies that involve the classification of underwater organisms such
as plants and animals are usually highly dependent on images and videos captured. In
underwater images and videos, the blue color is often the dominant color. Nonuniform
lighting, low contrast and diminished color are examples of underwater
environmental effects. Underwater images and videos are of poor quality due to the
nature of water and its density which is denser than air by approximately 800 times.
The main aim of this research isoto enhance the existing Integrated Color Model
(ICM) algorithm which is mainly used for underwater image enhancement. The
enhancement was done by making the stretching parameters adaptive rather than
using constant parameters. This was done by testing the current image to determine
which color was dominant and the stretching parameter will depend on this. The
enhanced ICM was then compared to the existing ICM using number of edges
generated by both algorithms and also by their histograms. For 50 images, the results
shown that the ICM generated images with 286731 edges while the Enhanced ICM
generated 306416 edges. Secondly, the research introduced the use of a shared
memory programming model to minimize the time required to enhance underwater
images and videos by the enhanced ICM. The results obtained showed that when the
image size (frame size in terms of video) was larger than 1 MByte and the number of
threads was three, the benefit of parallelization was more noticeable.
Description
Keywords
Underwater images and videos are of poor quality , due to the nature of water