An underwater target recognition method based on multimodal fusion

Abstract

The invention discloses an underwater target recognition method based on multi-modal fusion, comprising the following steps: (1) data collection, sonar signal data collection and marine environment data collection; (2) data fusion and spectrum extraction, and The environmental data is fused to obtain one-dimensional data, and the Lofar spectrum is extracted from the sonar signal; (3) the model is built, and a multi-modal fusion model based on convolutional neural network is constructed. The marine environmental data uses a one-dimensional convolutional neural network and Lofar spectrum. The figure uses a two-dimensional convolutional neural network; (4) target recognition, input the collected data into the corresponding network for training and testing, and obtain the underwater target recognition results. The method disclosed in the present invention introduces marine environmental data, combines with Lofar spectrum, and performs multi-modal fusion, and the combination of the two can provide more accurate and richer feature information for water-phase target identification.

Description

technical field [0001] The invention relates to the technical field of ocean detection, in particular to an underwater target recognition method based on multimodal fusion. Background technique [0002] The 21st century is the ocean century, and mankind will fully understand, develop and utilize the ocean. The development of modern science and technology has brought human beings into a period of large-scale development and utilization of the ocean. However, the marine environment is extremely complex, and the ocean world is full of unknowns and dangers. Humans cannot come and go as freely in the ocean as they do on land. Therefore, we need to use various technologies to deepen our understanding of the ocean. Underwater unmanned vehicle is a small submersible that can replace humans in the ocean. It can not only conduct underwater research, but also has extremely important strategic significance. To this end, underwater vehicles need to have a complete underwater submersibl...

AI Technical Summary

Problems solved by technology

[0006] (1) There are complex situations such as environmental noise, different types of sound sources, and multiple interference sources in the actual ocean, which lead to serious interference and noise in the signal collected by sonar, so that underwater targets cannot be accurately judged

[0007] (2) The principle of time-frequency feature extraction is simple and easy to implement, but prior knowledge is required to set the parameters, and fixed parameters will make the recognition generalization of such features weak in complex marine environment conditions

Images