Examination of automatic detection and tracking of ships on camera image in marine environment

It is very important to realize the safer marine transportation system. This paper describes a novel method to detect and tracking ships using a machine vision to reduce marine accidents. The proposed method has two stages; detection and tracking. In the detection stage, edges on a sea image are calculated and bounding rectangles that have the many pixels with the strong edge are selected by morphological processing. Then, the bounding rectangles are judged “ship” or not by the support vector machine. In the tracking stage, the ship was tracked by the particle filter based on a color histogram inside the bounding rectangle. Experimental results show that ships are detected and tracked on movie images in marine environment.