Abstract
Visible image quality is very susceptible to changes in illumination, and there are limitations in ship classification using images acquired by a single sensor. This study proposes a ship classification method based on an attention mechanism and multi-scale convolutional neural network (MSCNN) for visible and infrared images. First, the features of visible and infrared images are extracted by a two-stream symmetric multi-scale convolutional neural network module, and then concatenated to make full use of the complementary features present in multi-modal images. After that, the attention mechanism is applied to the concatenated fusion features to emphasize local details areas in the feature map, aiming to further improve feature representation capability of the model. Lastly, attention weights and the original concatenated fusion features are added element by element and fed into fully connected layers and Softmax output layer for final classification output. Effectiveness of the proposed method is verified on a visible and infrared spectra (VAIS) dataset, which shows 93.81% accuracy in classification results. Compared with other state-of-the-art methods, the proposed method could extract features more effectively and has better overall classification performance.
Highlights
Ship classification plays an important role in military and civilian fields, such as maritime traffic, fishing vessel monitoring, maritime search and rescue, etc. [1,2]
CNN_CFF and MSCNN_CFF represent concatenated feature fusion of infrared image features and visible image features extracted by convolutional neural network (CNN) and multi-scale convolutional neural network (MSCNN), respectively
Classification accuracy using feature fusion methods is higher than the baseline method, which means that fusing visible image features and infrared image features can complement information from multiple sources and improve classification performance
Summary
Ship classification plays an important role in military and civilian fields, such as maritime traffic, fishing vessel monitoring, maritime search and rescue, etc. [1,2]. Li et al [14] proposes a CNN-based ship classification method which designed two networks built on AlexNet and GoogleNet, and used a pre-trained model on the ImageNet dataset for transfer learning. There is relatively little research on ship classification methods based on visible and infrared images fusion. Considering that a single feature may not be comprehensive to represent ship images, the study proposes ship classification based on attention mechanism and multi-scale convolutional neural network (MSCNN). (3) The attention mechanism is applied to the allow further uselayer of the information within in different modalmap, images, such improving that a concatenated fusion tocomplementary enhance important local details the feature thereby more detailed ship object description can be obtained.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
