Affiliations: [a] College of Economics and Management, Minjiang University, Fuzhou, China
| [b] College of Physics and Electronic Information Engineering, Minjiang University, Fuzhou, China
| [c] School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China
| [d] School of Energy and Power Engineering, Wuhan University of Technology, Wuhan, China
| [e] National Engineering Research Center of Water Transport Safety Fujian Branch, Minjiang University, Fuzhou, China
| [f] Department of Computer Engineering. University of Alcalá, Alcalá de Henares (Madrid), Spain
| [g] School of Engineering, Ocean University of China, Tsingdao, China
Correspondence:
[*]
Corresponding author. Wei He, College of Economics and Management, Minjiang University, Fuzhou 350108, China. Tel.: +86 18606990698; E-mail: [email protected].
Abstract: Rich image information is one of the important means through which unmanned surface vehicles effectively and reliably identify targets during autonomous navigation. However, the adaptability of traditional artificial design feature methods in target representation and differentiation remains limited due to the diversity of ship target types, different scales, and complex and dynamic outdoor scenes. This study proposed a ship target recognition method based on single shot multi-box detector (SSD) deep learning. First, training and test sample sets were constructed by acquiring and creating a ship’s target image and background image under different types and scenes in an actual river environment. Subsequently, the sample set was used to train and optimize the SSD depth model to achieve adaptive extraction and recognition of target features. Lastly, ship identification experiments with different background environments and foreground targets were performed to test the effectiveness of the proposed method. The support vector machine method based on artificial feature extraction was used for the comparative experiments. Experiment results showed that the SSD-based deep learning method achieved better results than the artificial design feature method in terms of recall and precision rates.
