AISB convention 2017

  In the run up to AISB2017 convention, I've asked Joanna Bryson, from the organising team, to answer few questions about the convention and what comes with it. Mohammad Majid al-Rifaie ( Tu...


Harold Cohen

Harold Cohen, tireless computer art pioneer dies at 87   Harold Cohen at the Tate (1983) Aaron image in background   Harold Cohen died at 87 in his studio on 27th April 2016 in Encintias California, USA.The first time I hear...


Dancing with Pixies?...

At TEDx Tottenham, London Mark Bishop (the former chair of the Society) demonstrates that if the ongoing EU flagship science project - the 1.6 billion dollar "Human Brain Project” - ultimately succeeds in understanding all as...


Computerised Minds. ...

A video sponsored by the society discusses Searle's Chinese Room Argument (CRA) and the heated debates surrounding it. In this video, which is accessible to the general public and those with interest in AI, Olly's Philosophy Tube ...


Connection Science

All individual members of The Society for the Study of Artificial Intelligence and Simulation of Behaviour have a personal subscription to the Taylor Francis journal Connection Science as part of their membership. How to Acce...



AISB opportunities Bulletin Item

JOB : Postdoc Position - Adelaide, South Australia

Australian Centre for Visual Technologies
University of Adelaide
South Australia

Rapid interactive scene modelling from video

Research areas: Computer Vision, Structure from Motion

The successful applicant will join an established and successful team
lead by Dr Anton van den Hengel, Dr Anthony Dick, and Prof Philip Torr
and will work on developing methods for rapid interactive scene modeling
from video sequences. The position is initially for 2 years and will be
available from mid 2007.

Project background: The recovery of 3D models from video has for a
number of years been a goal of both the computer vision and graphics
communities. In computer vision, several systems have been developed to
automatically recover a cloud of 3D scene points from a video sequence.
However these are vulnerable to ambiguities in the image data,
degeneracies in camera motion, and a lack of discernible features on the
model surface. These difficulties can be overcome by manual intervention
in the modelling process. In the extreme case, a modelling package such
as Blender3D can used to build a model manually, but it is difficult to
create a photo realistic result by this process. A more appealing option
is to use all of the information that can be derived from the video
using computer vision techniques to inform an interactive modelling
process. The question then arises: how should these interactions be
implemented so they are (a) intuitive to a non-expert user and (b)
powerful and informative to the underlying modelling engine, so that
only a small number of interactions are required?

Applicants should have a PhD in a relevant discipline, with a strong
background in computer vision, in particular in structure from motion
and Bayesian estimation.  Strong coding and mathematical skills are also
required. The successful applicant will work as part of a team of
researchers within the Australian Centre for Visual Technologies on
problems in interactive scene modeling.

Salary: From ,700 to ,215 (Australian Dollars) negotiable.

Closing Date: 29 June, 2007.  Further positions may become available,
however, so applications may be accepted after this date for those

Informal enquiries and applications may be addressed to
Dr. A van den Hengel, Australian Centre for Visual Technologies
University of Adelaide, Adelaide, South Australia 5005, Australia tel +61 8 8303 5309