Andrew Schofield

Email: a.schofield@aston.ac.uk

Phone:+44 (0)121 204 3313 

ROSSINI: Reconstructing 3D structure from single images: a perceptual reconstruction approach. 2019 - 2023: ESPRC funded joint with Surrey and Southampton.

ROSSINI will develop a new machine vision system for 3D reconstruction that is more flexible and robust than previous methods. Focussing on static images, we will identify key structural features that are important to humans. We will combine neural networks with computer vision methods to form human-like descriptions of scenes and 3D scene models. Our aims are to (i) produce 3D representations that look correct to humans even if they are not strictly geometrically correct (ii) do so for all types of scene and (iii) express the uncertainty inherent in each reconstruction. To this end we will collect data on human interpretation of images and incorporate this information into our network. Our novel training method will learn from humans and existing ground truth datasets; the training algorithm selecting the most useful human tasks (i.e. judge depth within a particular image) to maximise learning. Importantly, the inclusion of human perceptual data should reduce the overall quantity of training data required, while mitigating the risk of over-reliance on a specific dataset. Moreover, when fully trained, our system will produce 3D reconstructions alongside information about the reliability of the depth estimates.

Using Classification Images to Unlock Expertise in Judgements of 3D Aerial Geography. Co-funder Ordnance Survey.

The Ordnance Survey is the UKs leading mapping company providing authoritative mapping data to government, local authorities and business for the UK with an increasingly global reach. A key element of this work is photogrammetric surveying in which mapping data is created from 3D aerial images. While this task is performed well, the features used are not well understood and surveying skills are largely gained though experience. We have developed a novel technique to derive internal templates for 3D geographical features. This technique will be used to improve training and to develop computer vision systems .

First year PY1505 Foundations of Contemporary Psychology

Second year PY2501 Research Methods and Data Analysis

Final year PY3024 Visual Perception and Illusions

BEng Electrical and Electronic Engineering, Brunel.

Diploma in Psychology (Conversion), Open.

PhD Communication and Neuroscience, Keele.

Hannah Broadbent (Joint University of Nottingham)

Emil Skog

Applied Vision Association (Member and past Chair).

Vision Sciences Society

British Machine Vision Association

Visual Image Interpreation In Humans and Machnies (EPSRC Network, Chair)

Member of EPSRC Peer Review College + occational panel member / chair

Oct 2020 - Present: College Director of Research Degree Programmes, Aston University.

Oct 2018 - Present: Reader in Psychology, Aston University.

2016 - 2018: Deputy Director of Education, College of Life and Environmental Sciences, University of Birmingham.

2006 - 2018: Senior Lecturer, Psychology, University of Birmingham.

1999 - 2006: Lecturer, Psychology, University of Birmingham.

1996 - 1999: Research Fellow, University of Birmingham.

1995 - 1996: Higher Scientific Officer, Forensic Science Service.

1993 - 1995: Research Fellow, Electronics, Brunel University.

Director of Research Degree Programmes: HLS (2020 - )

Director of Operations, Psychology (2021 - )

Deputy Head of Psycology (2019 - 2021)

Acting Dean of the Aston Graduate School (Feb-July 2020)