Underwater Target Detection Based on ANSYS Finite Element Analysis and SVM

Abstract

With the gradual development and utilization of marine resources, more and more attention has been paid to the study of marine technology. At present, sonar imaging technology is used to collect image data sets under seawater, but this method is costly. Aiming at this problem, A method of collecting image data sets was proposed through ANSYS finite element analysis simulation to realize underwater target detection. The finite element software ANSYS workbench platform was used to establish a finite element simulation model of underwater objects. The wave passed through the underwater objects and the image data set was collected from the simulation results. Two features of the directional gradient histogram and gray level co-occurrence matrix of the image were extracted, and then these features were used as inputs of SVM classifier. The result was applied to detect whether there was an object underwater.