The main bottleneck limiting the use of traditional ship classification methods is the manual extraction of ship images before classification. To solve this problem, a ship classification method based on a convolutional neural network (CNN) is proposed in this paper. A CNN model can autonomously extract image features, avoiding complex feature selection and extraction processes. In view of the problem of an insufficient number of ship samples, transfer learning was applied to train the model using the ImageNet dataset, effectively alleviating the over-fitting phenomenon in the training process. Experiments showed that the CNN model had an accuracy of 98% in ship classification using the SHIP-3 dataset. The CNN was robust to external environmental challenges – such as illumination – the accuracy of ship classification in foggy and night-time conditions reaching 75%, greatly exceeding the performance of traditional machine learning algorithms.
Ship classification based on convolutional neural networks
Ships and Offshore Structures ; 17 , 12 ; 2715-2721
2022-12-02
7 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
Covert photo classification by deep convolutional neural networks
British Library Online Contents | 2017
|Convolutional Neural Networks for Classification of Drones Using Radars
DOAJ | 2021
|Automated Truck Taxonomy Classification Using Deep Convolutional Neural Networks
Springer Verlag | 2022
|