The Australian National University
CECS Home | ANU Home | Search ANU | HORUS | Staff Home

Help | Seminars List | Add Seminar | Edit Seminars | Tips for organisers | RSS | ics Calendar | Search |

Send comments about this website to seminar-master@cecs.anu.edu.au


Contact: luke.fletcher@anu.edu.au

INFOENG SEMINAR SERIES Colloquium Series

The Hough transform, probability and shape detectors

Dr. Nick Barnes (ASSeT, NICTA.)


DATE: 2005-12-09
TIME: 11:00:00 - 12:00:00
LOCATION: RSISE Seminar Room, ground floor, building 115, cnr. North and Daley Roads, ANU



ABSTRACT:
P V C Hough patented an algorithm in 1962 for shape detection. Its application to finding lines in images is still one of the most commonly used algorithms in computer vision and image processing. The algorithm follows the principle of maximum likelihood estimation and has been generalised to find arbitrary parametric shapes. In this seminar, I will give an overview of the algorithm, its probabilistic interpretation, and our recent work on generalising the algorithm to space variant images. I will then introduce the regular polygon detector that uses a dimension reduction technique to derive a real-time solution to a higher dimensional problem. I will also present the resulting algorithms' application to real-time tracking, and the detection of different types of sign.



BIO:
Nick Barnes received the BSc (Hons) and PhD degrees from the University of Melbourne in 1991, and 1999 respectively. In between he worked for a consulting firm in telecommunications. Prior to joining NICTA, Dr Barnes has been a lecturer in computer science and software engineering at the University of Melbourne and a postdoctoral fellow at the LIRA Lab at the University of Genoa, Italy. Dr Barnes is a senior researcher at National ICT Australia in the ASSeT program, and is leading the MRI project, exploring ageing, neuroanatomy and cognition. Dr Barnes's key interests are in robotic and biological vision, or more generally, embodied perceptual systems, includinginsects, humans, intelligent road vehicles, and ground-based robots. Underlyingthese areas are the problems of active perception, visual motion, embodied scene understanding, navigation, and cognition, particularly as it relates to perception.



MEDIA:
051209_barnes.pdf
051209_barnes_video_redirect.html