Underwater multi-source acoustic image substrate classification method and system based on decision-making level fusion

Abstract

The invention discloses an underwater multi-source acoustic image substrate classification method and system based on decision-making level fusion. The method comprises the following steps: acquiringa geomorphic image, a topographic image and a stratum profile image under a unified space coordinate system; determining a landform segmentation image, a terrain segmentation image and a stratum profile segmentation image; performing feature extraction on each segmented image to obtain landform features, topographic features and stratum features; respectively inputting the geomorphic features andthe topographic features into a plurality of trained machine learning classification models to obtain a plurality of first classification results and a plurality of second classification results, andinputting the stratum features into the trained machine learning classification models to obtain a third classification result; and fusing the plurality of first classification results and the plurality of second classification results based on a D-S evidence theory, or fusing the plurality of first classification results, the plurality of second classification results and the third classificationresult to obtain a substrate classification result of the underwater multi-source acoustic image. According to the invention, automatic and high-precision classification of underwater substrates canbe realized.

Description

technical field [0001] The invention relates to the technical field of underwater acoustic image classification, in particular to an underwater multi-source acoustic image bottom classification method and system based on decision-making level fusion. Background technique [0002] Substrate classification refers to the classification of bottom materials (such as mud, sand, coarse sand, gravel, reef, etc.) of water bodies such as oceans, lakes, and rivers. The classification of underwater sediments is of great significance to underwater scientific research, resource development, environmental protection and underwater rights protection. Multi-source detection such as side-scan sonar, multi-beam sonar system and shallow strata profiler are commonly used techniques for acoustic sediment classification. By analyzing and interpreting the multi-source acoustic images obtained by the above three types of acoustic equipment, the sediment Classification of types. Multi-source acoust...

AI Technical Summary

Problems solved by technology

The manual discrimination method uses multi-source acoustic data such as side-scan sonar, multi-beam and shallow stratum section for underwater survey and bottom classification through manual comprehensive interpretation. This method has been widely used in underwater survey work at home and abroad. application, but this method relies on the experience of the discriminator, the discriminant process is not easy to go back, and the workload is huge when it is applied in a large range, and the classification accuracy needs to be improved

The essence of the general fusion method is to realize the spatial integration of multi-source and heterogeneous acoustic image data, and integrate the multi-source acoustic images in a unified coordinate system according to their spatial relationship, but it has not formed specific applications such as underwater substrate classification. The core fusion method and system cannot realize automatic underwater bottom classification

The more important purpose of the image fusion method of multi-source acoustic data is to obtain higher-quality image data or useful information through fusion, which mainly focuses on fusing multi-source acoustic images at the data level to improve data quality. The substratum profile information has not been effectively integrated and utilized

Images