Heriot-Watt University Riccartton, Edinburgh

Sidescan and forward looking sonars are some of the most widely used imaging systems for obtaining large scale images of the seafloor, and their use continues to expand rapidly with their increased deployment on Autonomous Underwater Vehicles. However, it is difficult to extract quantitative information from the images generated from these non-linear processes, in particular for the detection and extraction of information regarding objects within these images. This paper will present techniques for the extraction and classification of objects which through the inclusion of a priori information on the actual sonar process provide robust segmentation and data extraction. 1