Reliable vessel detection can improve safety and security in maritime environment. Recently, application of Deep Learning (DL)-based detectors have become popular in autonomous vehicles. The aim of this paper is to study how much a pretrained DL model on a domain-specific marine data can improve the performance of the detectors for vessel detection? To this end, we trained state-of-the-art DL-based detectors (Faster R-CNN [1], R-FCN [2] and SSD [3]) using an open source generic object detection COCO dataset [4] and a marine SeaShips dataset [5]. The performance of these detectors are explored based on different feature extractors. Moreover, we investigate the effect of object size on the detection accuracy. To obtain results, we collected a real marine dataset by a sensor system onboard a vessel in the Finnish archipelago. This system is used for developing autonomous vessels, and records data in a range of operation and climatic conditions. The experimental results show that Faster R-CNN with ResNet101 achieves the highest object detection accuracy with mean average precision of 75.2%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Transfer Learning for Maritime Vessel Detection using Deep Neural Networks


    Contributors:


    Publication date :

    2021-09-19


    Size :

    472428 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Aerial Maritime Vessel Detection and Identification

    Kulas, Antonella Barisic / Petric, Frano / Bogdan, Stjepan | IEEE | 2025


    MARITIME VESSEL STABILIZER

    TEPPIG JR / WHANG JAMES S | European Patent Office | 2025

    Free access

    Maritime Vessel Stabilizer

    TEPPIG JR WILLIAM M / WHANG JAMES S | European Patent Office | 2024

    Free access

    Maritime Vessel Detection and Tracking under UAV Vision

    Li, YongShuai / Yuan, Haiwen / Wang, Yuan et al. | IEEE | 2022


    Maritime Target Detection Method Based on Deep Learning

    Fu, Huixuan / Li, Yuan / Wang, Yuchao et al. | British Library Conference Proceedings | 2018