Ship detection in satellite imagery is an important application in marine time security. This can also be majorly used in sea pollution control, oil leakage detection and other illegal fisheries. A deep learning approach can be used to detect the ships from satellite imagery. For this, pre-processing using image segmentation is done followed by the bounding box detection from YOLOv3. This is done on a Kaggle ship dataset with 231722 images. After passing the training set to the model, the model can detect the region of ship followed by count of ships in the given image. This can be tested with other deep learning approaches to increase the detection accuracy. Furthermore, the detection region and the count of ships can be passed to a hash function which in turn increases the security of the model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Region based Detection of Ships from Remote Sensing Satellite Imagery using Deep Learning


    Beteiligte:
    Anusha, Ch. (Autor:in) / Rupa, Ch. (Autor:in) / Samhitha, G. (Autor:in)


    Erscheinungsdatum :

    23.02.2022


    Format / Umfang :

    369132 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    AUTOMATED REMOTE SENSING FOREST INVENTORY USING SATELLITE IMAGERY

    Shtanchaev, Abduragim / Elelimy, Sara / Sutyrina, Olga et al. | TIBKAT | 2021


    Illegal Boat Detection Using Satellite Imagery with Deep Learning

    Singh, Anvi / Prasad, Aarav / G, Sumathy | IEEE | 2024



    Road Recognition From Remote Sensing Imagery Using Incremental Learning

    Zhang, Jing / Chen, Lu / Wang, Chao et al. | IEEE | 2017


    Understanding the Revenue Potential of Satellite-Based Remote Sensing Imagery Providers

    Wong, F. C. / IEEE | British Library Conference Proceedings | 2005