A method and system for classifying sea bottom based on synthetic aperture sonar images

Abstract

The present invention relates to a method for classifying seabed substrates based on synthetic aperture sonar images. The method is used to classify the submarine substrates of synthetic aperture sonar images, including: step 101) reading in the seabed substrates to be classified Synthetic aperture sonar image; Step 102) Calculating the gray level co-occurrence matrix of the synthetic aperture sonar image; Step 103) Obtaining the characteristic parameters that can reflect the information of the bottom of the seabed based on the gray level co-occurrence matrix, and all parameters form a feature vector that can reflect the texture feature ; Step 104) compare the eigenvectors with the statistical information, and then complete the classification of the seabed substrate; the statistical information is: according to the characteristics of different substrate types in the synthetic aperture image, use all types of seabed substrate gray level co-occurrence matrix The texture feature parameters are used to construct feature vectors; and all feature vectors are trained separately to obtain typical values ​​corresponding to all seabed subsurface areas, and all typical values ​​are stored to form statistical information.

Description

technical field [0001] The invention relates to the field of seabed bottom classification, in particular to a sea bottom classification method and system based on synthetic aperture sonar images. Background technique [0002] The classification study of seabed bottom (seabed sediment) is the basis of geophysical exploration, marine surveying and mapping, marine engineering and other application fields, and it has very important significance in civil and military aspects. Ocean engineering, offshore oil development, submarine base selection, and mine sweeping operations in the military field must understand the type of bottom of the seabed. [0003] Acoustic method telemetry seabed sediment type has become a rapid and reliable seabed sediment classification method because of its high efficiency, continuous and abundant data acquisition and other characteristics. Synthetic Aperture Sonar (SAS, Synthetic Aperture Sonar) is a high-resolution underwater imaging sonar that can ob...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the technical problems of low classification accuracy caused by only relying on the grayscale information of synthetic aperture sonar images when classifying the sea bottom in the prior art, thereby providing a sea bottom classification based on synthetic aperture sonar images. Substrate Classification Method and System

Images