Ship Tracking Using Background Subtraction and Inter-Frame Correlation

Ship detection and tracking is an essential requirement for maritime surveillance systems. Background subtraction is used for detecting moving objects in video images. Then the moving targets are segmented by an improved method using extended-maxima transform with an adaptive threshold. Furthermore, a compensation method is proposed so as not to miss target information due to a gradual change when target in or out of the field of view. And then the target will be tracked with an inter-frame correlation method. Finally, the centroids of the target region in each frame are obtained to perform a ship tracking. The experimental results demonstrate that the proposed method is very efficient. The approach could be applied to automatic video monitoring in sea port security, maritime transportation, and ocean engineering managements.