Algorithm for Imaging Sonar Target Detection based on Geometry Characteristic and SVM

Abstract

The attack from small speedboat and underwater robot is becoming more and more serious. And most powerful countries have installed underwater surveillance systems to protect port, ship, seashore depository and anchorage. The detection technology of underwater target is the most important technology in the process of surveillance. In order to take good advantage of the target’s geometry characteristic and classification function of SVM(Support Vector Machine), an algorithm for imaging sonar target detection based on geometry characteristic and SVM is proposed in the paper. The experiment results are presented and show that this algorithm is in high detection rate under complex underwater circumstance.