Abstract
Maritime activities are essential aspects of human society. Accurate classification of ships is vital for maritime surveillance and meaningful to numerous civil and military applications. However, most studies conducted are limited to the coarse-grained ship classification. Few studies on fine-grained ship classification have been undertaken despite its accuracy and practicability. In this study, we construct a new benchmark for fine-grained ship classification which consists of 23 fine-grained categories of ships. Besides the category label, the benchmark contains several other attribute information. To solve the problem of interclass similarity, an attribute-guided multilevel enhanced feature representation network (AMEFRN) is proposed. Concretely, a multilevel enhanced visual feature representation is designed to fuse the reweighted regional features in order to focus more on the silent region and suppress the other regions. Further to this, considering the complementary role of attribute information in ship identification, an attribute-guided feature extraction branch is proposed, which extracts the auxiliary attribute features by utilizing the attribute information as supervision. Finally, the attribute features and the enhanced visual features jointly function as a feature representation for classification. Compared to other existing classification models, AMEFRN has better performance with an overall accuracy rate of 93.58% on the established fine-grained ship classification dataset. Moreover, it can be easily embedded into most CNN models as well as trained end-to-end.
Highlights
M ARITIME activities, for instance, maritime transportation, commercial trades, maritime security, and antiillegal activities, are important to the human society, as theyManuscript received January 8, 2020; revised February 26, 2020 and March 9, 2020; accepted March 13, 2020
Multilevel convolutional visual features are extracted from VGG16 and the local features are weighed by an RNN-based attention mechanism to get an enhanced visual feature representation
A 23-category fine-grained ship classification dataset called FGSC-23 is established for this investigation, which compensates the lack of relevant data
Summary
M ARITIME activities, for instance, maritime transportation, commercial trades, maritime security, and antiillegal activities, are important to the human society, as theyManuscript received January 8, 2020; revised February 26, 2020 and March 9, 2020; accepted March 13, 2020. Numerous ships of different types cruise the sea and the classification of ships through optical remote sensing images constitutes one of the basic technologies for marine surveillance [1], [2]. This technology has numerous civil and military applications [3]. Level-3 classification refers to the fine-grained classification where ships are distinguished into their precise categories. A significant number of studies conducted mainly address the first two levels of classification, with only a few methods and datasets proposed for the fine-grained ship classification. More precise and detailed classification in this level can be more practical and valuable compared to the other two levels of classifications in many applications [5]
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
