Seafloor Classification from Multibeam Backscatter Data Using Learning Vector Quantization Neural Network

We utilize the seafloor backscatter strength data of each beam from multibeam sonar systems and the automatic classification technology to get the seafloor type identification maps.We primarily study on the seafloor classification using learning vector quantization(LVQ) neural network method.Using this classification method,we can rapidly identify all kinds of seafloor types,such as sand,gravel and rock in the experimental surveying areas.