Frequent adverse weather conditions at sea, particularly fog and haze, significantly degrade the quality of images captured by optical devices. Due to reduced visibility at sea and the scattering of atmospheric light in foggy conditions, which lowers scene contrast, ship detection in foggy environments remains a challenging task. Most existing ship detection methods are designed based on normal weather conditions, and they lack adequate consideration of the image quality degradation caused by the complex and dynamic maritime environment, which leads to reduced detection accuracy. This paper proposes a two-stage ship detection framework tailored for foggy maritime scenarios. In the first stage, a dehazing network is applied to process the foggy images, producing higher-quality inputs for detection. In the second stage, the framework employs an object detection network to identify ship objects within the enhanced images. Experimental results demonstrate that the proposed detection framework significantly improves ship detection performance in foggy scenes, with an increase of 22.3% in mAP on the synthesized fog dataset MVDD13. Additionally, it achieves a 2.2% improvement in mAP on the FMNSDD dataset we established.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    FNSD: A Ship Detection Framework Based on Foggy Maritime Navigation Scenarios


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Jia, Limin (editor) / Ou, Dongxiu (editor) / Liu, Hui (editor) / Zong, Fang (editor) / Wang, Pangwei (editor) / Zhang, Mingfang (editor) / Lv, Yuezheng (author) / Si, Lingyu (author) / Shen, Xingchen (author) / Huang, Shouyou (author)

    Conference:

    International Conference on Artificial Intelligence and Autonomous Transportation ; 2024 ; Beijing, China December 06, 2024 - December 08, 2024



    Publication date :

    2025-03-31


    Size :

    8 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    Enhanced YOLOv9 for Pedestrian and Vehicle Detection in Foggy Traffic Scenarios

    Xiao, Xianghui / Zeng, Junbin / Guan, Luchang et al. | IEEE | 2024


    Foggy Drone Teacher: Domain Adaptive Drone Detection Under Foggy Conditions

    Guida Zheng / Benying Tan / Jingxin Wu et al. | DOAJ | 2025

    Free access


    Foggy forecast

    Cotey, Angela | IuD Bahn | 2007