Improving of ViBE algoritihm for moving target detection at maritime surveilance

Abstract

At the research for moving target detection at maritime surveilance with a fixed camera stationed at the shore, Background Subtraction is the best method that can be used for sea which is a dynamic environment due to factors such as wave, wave foam, rudder water, weather condition, sunlight reflected on the sea, When the methods that give the best results by using background subtraction are examined, it is seen that the ViBE algorithm made for motion detection is suitable. However, it has been observed that sometimes there are erroneous evaluations in the foreground and background classification when we run the ViBE algorithm on marine surveillance, there may be noise in the image, and the target may have a foreground which includes a small part of the target but not the whole. In order to overcome these situations, some improvements have been made on the algorithm and appropriate results have been obtained.