Small Fishing boat classification and recognition method based on GASF temporal graph coding and EMPViT model

Abstract

Efficient management of small vessels is crucial for maritime operations, and effective classification and identification algorithms for small fishing vessels are key to enhancing ship management. This paper proposes a classification and recognition method for small fishing boats based on GASF sequence diagram coding, addressing the complex and challenging recognition environment. The method focuses on four typical small fishing vessels, utilizing Gramian Summation Angular Field (GASF) time series images and the Efficiency MPViT (EMPViT) model. Unlike traditional approaches, this study initially employs a high-precision laser sensor to gather one-dimensional contour data of fishing boats. Subsequently, the polynomial fitting method is used to delineate the shape of the fishing boat contour, which is then encoded into a two-dimensional time series image using the GASF encoding method. The enhanced EMPViT model is then applied to classify and identify small fishing vessels, with the results verified through ablation experiments. These experiments demonstrate that the EMPViT model surpasses traditional neural network models such as CNN and ViT in both accuracy and performance, achieving a peak accuracy of 99.98%.