Determination of The Ship Motion Direction with Digital Image Processing on Sea Water Surface to Avoid Collisions

Abstract

As the largest archipelagic country in the world, Indonesia has 17,499 islands from Sabang to Merauke. There is a country with an area of water greater than the land area. Data on shipping accident investigations from the National Transportation Safety Committee (NTSC) throughout 2010-2016 of fifty-four accident cases at sea, seventeen of which were accidents caused by collisions on ships in Indonesian waters. This is equivalent to twenty percent of accidents that have occurred, a human error causes as many as 80% of collision accidents from the crew or people in the sea transportation system, and natural factors or machinery cause only a few. The success of this research aims to avoid ship breaking, by giving directions on the direction of the ship obtained by the results of digital image processing. This study proposes a digital image processing model on sea surface using object recognition. It used the morphological operation in the preprocessing stage; this method can remove non-uniform illumination and reflection in sea surface. Then, noise in the image data will decrease. The result of this object recognition will be used to determine the direction of ship movement. Experimental results with our own dataset verify the high efficiency of our proposed method.