Marine-organism-oriented lightweight aliasing dense network classification method and system

Abstract

The invention relates to a marine-organism-oriented lightweight aliasing dense network classification method and system, and the method comprises the steps: obtaining a marine organism image, loading the marine organism image into a pre-established and trained aliasing dense network model, and obtaining a classification result; the aliasing dense network model is a convolutional neural network, a dense block is arranged in the convolutional neural network, the dense block comprises a plurality of aliasing network units, and the plurality of aliasing network units are connected in a dense connection mode; the aliasing network unit comprises a first grouping convolution layer, a batch regularization layer, a channel aliasing layer, a depth separable convolution layer, a second grouping convolution layer and a cascading layer which are connected in sequence, the cascading layer is connected with the input of the aliasing network unit and the output of the second grouping convolution layer, and the output of the cascading layer is connected with a linear rectification function. Compared with the prior art, the method has the advantages that more useful information can be obtained, model parameters are reduced, information fusion is realized, and the network training speed is increased while the network classification precision is improved.

Description

technical field [0001] The invention relates to the field of image classification, in particular to a light-weight aliasing dense network classification method and system for marine organisms. Background technique [0002] The identification of marine fish species, habitat distribution, spawning ground distribution, etc. are important research contents of marine biological science and marine environmental science. Information science and technology has become an important means for marine biologists and environmental scientists to conduct the above research. The core issue is how to accurately classify marine fish targets based on the obtained visual data. [0003] There are many visually similar fish in the ocean, and it is difficult to distinguish them accurately without professional knowledge of marine biology. [0004] Most of the existing methods for marine biological classification through neural networks have defects such as large amount of calculation, high energy ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a light-weight aliasing dense network classification method and system for marine organisms in order to overcome the defects of the above-mentioned prior art, such as large amount of calculation, high energy consumption, and poor classification accuracy.

Images