Fast Corner Detection Using a Spiral Architecture

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Downloads (Pure)

Abstract

Fast image processing is a key element in achieving real-time image and video analysis. Here, a novel framework based on a spiral architecture is used to facilitate fast image processing, in particular, fast corner detection. Unlike a conventional image addressing scheme where the picture elements are indexed using two-dimensional Cartesian coordinates, a spiral addressing scheme enables the image to be stored and indexed as a one-dimensional vector. Image processing is hastened through the combined use of the one-dimensional structure and a lookup table. The performance is evaluated by the application of a corner detector based on the Harris corner detection algorithm. The results demonstrate the efficiency of the proposed approach compared with a typical two-dimensional implementation.
Original languageEnglish
Title of host publicationUnknown Host Publication
PublisherIrish Pattern Recognition and Classification Society
Number of pages7
ISBN (Print)978-0-9934207-1-9
Publication statusE-pub ahead of print - 3 Nov 2016
EventIrish Machine Vision and Image Processing Conference 2016 - NUI Galway, Ireland
Duration: 3 Nov 2016 → …

Conference

ConferenceIrish Machine Vision and Image Processing Conference 2016
Period3/11/16 → …

Keywords

  • Fast Image Processing
  • Spiral Architecture
  • Corner Detection
  • Lookup Table
  • Eye Tremor

Fingerprint Dive into the research topics of 'Fast Corner Detection Using a Spiral Architecture'. Together they form a unique fingerprint.

  • Cite this

    Fegan, J., Coleman, SA., Kerr, D., & Bryan, S. (2016). Fast Corner Detection Using a Spiral Architecture. In Unknown Host Publication Irish Pattern Recognition and Classification Society.