Chinese Journal of Ship Research, Volume. 19, Issue 5, 188(2024)

Lightweight and robust ship detection method driven by self-attention mechanism

Feng MA1...2, Zihui SHI1,2, Jie SUN3, Chen CHEN3,4, Xianbin MAO5 and Xinping YAN2 |Show fewer author(s)
Author Affiliations
  • 1School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan 430063, China
  • 2Intelligent Transportation Systems Research Center, Wuhan University of Technology, Wuhan 430063, China
  • 3Nanjing Smart Water Transportation Technology Co., Ltd, Nanjing 210028, China
  • 4School of Computer Science and Technology, Wuhan Institute of Technology, Wuhan 430205, China
  • 5Zhoushan Haihua Passenger Transport Co., Ltd, Zhoushan 316111, China
  • show less

    Objective

    It is vital to detect and track ships during coastal monitoring and ship navigation over long distances in complex circumstances. However, due to their small size and unclear features, they can be readily confused with shorelines, noise, and rocks, making them sometimes difficult to spot immediately. To address this issue, a novel ship detection method called ShipDet is proposed which significantly improves performance through the design of a dedicated backbone network, improved feature extraction process, and constrained microscopic detection heads.

    Method

    First, this method constructs a feature fusion and extraction network that is highly sensitive to small objects by integrating the Swin Transformer module (STR) with the classic CSPDarknet53 network. This enhances the correlation between small target features and the environment, establishing associations between ships and waterways, ships and other ships, and ships and coastlines, while suppressing irrelevant information. Subsequently, considering the uneven distribution and minor scale variations of ship targets in the dataset, two detection layers are retained to reduce model parameters and further enhance model performance. Moreover, the method employs the SCYLLA-IoU (SIoU) loss function to constrain the detection heads, thereby reducing regression freedom and improving detection accuracy and robustness.

    Results

    To validate the proposed method, a dataset called 2023ships is established which consists of up to 9 000 samples covering various scenarios such as inland rivers, coastal areas, daytime, nighttime, and foggy weather. During testing, the proposed method demonstrates superior overall ship detection performance compared to other algorithms, with a mAP of 92.9%, a precision rate of 92.1%, and a parameter size of 35 366 310.

    Conclusion

    The proposed method can greatly benefit the fields of maritime monitoring and intelligent navigation.

    Keywords
    Tools

    Get Citation

    Copy Citation Text

    Feng MA, Zihui SHI, Jie SUN, Chen CHEN, Xianbin MAO, Xinping YAN. Lightweight and robust ship detection method driven by self-attention mechanism[J]. Chinese Journal of Ship Research, 2024, 19(5): 188

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Weapon, Electronic and Information System

    Received: May. 30, 2023

    Accepted: --

    Published Online: Mar. 14, 2025

    The Author Email:

    DOI:10.19693/j.issn.1673-3185.03389

    Topics