Browse/search for people

Publication - Professor Walterio Mayol-Cuevas

    Visual Odometry for Pixel Processor Arrays

    Citation

    Bose, L, Chen, J, Carey, S, Dudek, P & Mayol-Cuevas, W, 2017, ‘Visual Odometry for Pixel Processor Arrays’. in: 2017 International Conference on Computer Vision (ICCV 2017). Institute of Electrical and Electronics Engineers (IEEE), pp. 4614-6421

    Abstract

    We present an approach of estimating constrained egomotion
    on a Pixel Processor Array (PPA). These devices
    embed processing and data storage capability into the pixels
    of the image sensor, allowing for fast and low power
    parallel computation directly on the image-plane. Rather
    than the standard visual pipeline whereby whole images are
    transferred to an external general processing unit, our approach
    performs all computation upon the PPA itself, with
    the camera’s estimated motion as the only information output.
    Our approach estimates 3D rotation and a 1D scaleless
    estimate of translation. We introduce methods of image
    scaling, rotation and alignment which are performed
    solely upon the PPA itself and form the basis for conducting
    motion estimation. We demonstrate the algorithms on
    a SCAMP-5 vision chip, achieving frame rates >1000Hz at
    ~2W power consumption.

    Full details in the University publications repository