Satellite imagery has played a vital part in real-time monitoring and identification of threats in modern times. Accurately identifying illegal boats that are in or around the legal border of a country is a vital tool in defense sector of a country. Here we are using a large ship dataset containing unique ships, for which large number of images are used. We will use Convolution neural network for feature extraction and classification of images. The CNN is trained with function which increases the gap between the different kind of objects and ships and decreases the gap between the similar sea vessel. The ultimate goal of this project is to identify illegal sea vessels approaching or within the country's legal borders and to alert the appropriate authorities in real-time. By providing timely and accurate identification of potential threats, this system can significantly enhance maritime security and defense capabilities. Through continuous training and refinement using a large and diverse dataset, we aim to develop a highly reliable and effective tool for national defense, ensuring the safety and security of maritime borders.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Illegal Boat Detection Using Satellite Imagery with Deep Learning


    Contributors:
    Singh, Anvi (author) / Prasad, Aarav (author) / G, Sumathy (author)


    Publication date :

    2024-12-12


    Size :

    775939 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Comparing Deep Learning Performance for Aircraft Detection in Satellite Imagery

    Vergara, Victor M. / Wojcik, Jeremy J. / Kain, Evan T. et al. | IEEE | 2023



    Deep learning-based illegal parking enforcement system using wide-area detection images

    PARK YOUNG / CHUN SUNGHO / LEE GEUNWON | European Patent Office | 2022

    Free access


    Object detection in synthetic aerial imagery using deep learning

    Dabbiru, Lalitha / Goodin, Chris / Carruth, Daniel et al. | British Library Conference Proceedings | 2023