The waterway traffic is recently getting busier due to the strong development of the shipping industry. There are frequent collisions and other accidents between ships, it is necessary to detect these types of ships effectively to ensure waterway traffic safety. Ship detection technology based on computer vision employing optical remote sensing images has great significance to improve port management and maritime inspection. In recent years, convolutional neural networks (CNN) have achieved good results in ship target detection and recognition. In this paper, we train the YOLOv3 and the latest YOLOv4 model on the dataset. The experimental results show that YOLOv4 can be applied well in the field of ship detection and classification from optical remote sensing. Based on the obtained results, we compare the effectiveness of the models when applied to actual training on the same data set.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Comparison of YOLO Networks for Ship Detection and Classification from Optical Remote-Sensing Images


    Additional title:

    Lect. Notes in Networks, Syst.


    Contributors:

    Conference:

    International Conference on Hybrid Intelligent Systems ; 2022 December 13, 2022 - December 15, 2022



    Publication date :

    2023-05-25


    Size :

    10 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English






    Ship detection using SAR images based on YOLO at Cyprus’s coast

    Melillos, George / Hadjimitsis, Diofantos G. | SPIE | 2022


    Ship detection using SAR images based on YOLO (you only look once)

    Melillos, George / Kalogirou, Eleftheria / Makri, Despoina et al. | SPIE | 2023


    Weakly supervised ship detection in remote sensing images

    Guo, Chen / Tan, Zhiwen / An, Meng et al. | SPIE | 2022