Efficient pre-segmentation algorithm for sidescan-sonar images

This paper proposes a fast pre-segmentation algorithm based on matched filtering employing integral images. It is suitable for identifying regions of interest (ROI) in sonar images, in particular the detection of anomalies on the sea floor with focus on proud ground mines. Mines placed on the sea floor are still a vast threat in civil and military shipping. This potential risk is typically encountered by advanced sonar signal processing techniques and time consuming manual evaluation of the sonar data by a human operator. Due to mission specific time constraints a computer aided or even autonomous analysis of the huge amount of data is desired. A fast pre-segmentation of regions of interest (ROI) reduces not only the amount of data for the human operator and consecutive classification algorithms significantly; it also allows for a real time processing system applicable in autonomous underwater vehicles (AUV).