MURAL - Maynooth University Research Archive Library



    A Lightweight Region Proposal Network for Task Specific Applications


    O'Keeffe, Simon and Villing, Rudi (2019) A Lightweight Region Proposal Network for Task Specific Applications. In: 30th Irish Signals and Systems Conference (ISSC), Maynooth, Ireland, 2019. IEEE. ISBN 978-1-7281-2800-9

    [img]
    Preview
    Download (564kB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    Quickly and cheaply finding areas of interest within an image can save computationally intensive image processing in a vision pipeline. Existing region proposal networks are either too general (finding all objects in an image) or too complex (providing fine-tuned bounding boxes for classification). We propose a straightforward region proposal network that simply scores parts of the image based on whether or not they contain an object of interest. This calculation can be carried out quickly and for many applications including autonomous driving only a small fraction of the image area may contain objects of interest. We trained our network on an autonomous robot soccer dataset with similar characteristics to the popular KITTI autonomous driving dataset and achieved a recall greater than 95% while eliminating on average over 80% of the image area from further processing.

    Item Type: Book Section
    Keywords: Region Proposal; convolutional Neural Networks; real-time; vision pipeline;
    Academic Unit: Faculty of Science and Engineering > Electronic Engineering
    Item ID: 13571
    Identification Number: https://doi.org/10.1109/ISSC.2019.8904949
    Depositing User: Rudi Villing
    Date Deposited: 13 Nov 2020 16:12
    Publisher: IEEE
    Refereed: Yes
    Funders: Irish Research Council under their Government of Ireland Postgraduate Scholarship 2013, Science Foundation Ireland (SFI) under Grant Number 16/RI/3399
    URI:

    Repository Staff Only(login required)

    View Item Item control page

    Downloads

    Downloads per month over past year