Professor Toby Breckon

Computer Vision and Image Processing enabled by Machine Learning @tobybreckon

Toby Breckon is a Professor in the Department of Computer Science and Department of Engineering at Durham University and an academic tutor at St. Chads College.

Within the department(s), he leads research in computer vision, image processing and robotic sensing, with a strong emphasis on generalized machine learning and pattern recognition techniques, in addition to research-led teaching within the undergraduate Engineering and Computer Science programmes.

Experience

Prof. Breckon's current research spans a breath of computer vision, image processing and robotic sensing application domains including automotive sensing, X-ray security image understanding, automated visual surveillance and robotic sensing.

Within automotive, his team work with a number of major vehicle manufacturers on future automotive sensing solutions (2011- 2023) having originally commenced work in this area in the early days of intelligent driver assistance systems (2007-2010). The team's work on real-time visual saliency is patented (2013) and Prof. Breckon acted as a scientific advisor to tech startup Machines With Vision on aspects of autonomous vehicle sensing (2019-2023).

Within aviation security, his research work on X-ray image understanding pioneered the use of automated prohibited item detection algorithms within the sector and his team are credited with designing the first complete solution for threat image projection (TIP) within 3D CT security scan imagery (E&T Innovation Awards 2020, Highly Commended, Dynamites Technology Awards 2021, Innovator of the Year - Highly Commended). Their 3D TIP approach is now used globally by several major security scanner manufacturers, in numerous major international airports, and helps to secure over 500+ million passenger journeys per annum across five continents (2020).

The work of his team on anomaly detection is used by COSMONiO in their NOUS product. COSMONiO, founded by former members of his research team, was acquired by Intel in 2020.

His team were a collaborator in the original UK SAPIENT programme, and developed an infrared (thermal) based autonomous sensor unit to demonstrate 'the art of the possible' in multi-sensor wide area surveillance. SAPIENT resulted in substantial impact in the area of sensor interoperability across the defence and security sector (2016- 2023+). In collaboration with Blue Bear Systems, work from his team directly supported the development of intelligent payloads for "the largest collaborative, military focused evaluation of swarming uncrewed aerial vehicles (UAV) in the UK" (2021).

He has acted as a technical consultant on a broad range of industrial projects, supporting the development of several commercial products (2013- 2023), and as an expert technical witness in US Federal Court (2021).

The broader international reach of his research is further chronicled in three research impact case studies submitted as part of the UK National Research Evaluation Framework (REF) spanning work on X-ray security imaging, automotive sensing and wide-area visual surveillance (2020/21) and he is the recipient of the Durham University Award for Excellence in Knowledge Transfer in recognition of his outstanding contribution to the public benefit of research (2022).

In the early part of his research career, he led the technical development of real-time object detection for the Stellar Team's SATURN multi-platform robot system in the MoD Grand Challenge, going on to win the R.J. Mitchell Trophy (UK MoD Grand Challenge winners, 2008), the Finmeccanica Group Innovation Award (2009) and an IET Award for Innovation (Team Category, 2009).

His research work is recognised by the Royal Photographic Society Selwyn Award (2011) for a significant early career contribution to imaging science.

Background

Before joining Durham in 2013, he held faculty positions at the School of Engineering, Cranfield University, the UK's only postgraduate-only university, and the School of Informatics, University of Edinburgh. Prior to this he was a mobile robotics research engineer with the UK MoD (DERA) and latterly QinetiQ in addition to prior positions with the schools inspectorate OFSTED, the Scottish Language Dictionaries organisation and (dot-com) software house Orbital Software.

He has held a visiting faculty positions at ESTIA ( Ecole Supérieure des Technologies Industrielles Avancées), South-West France, Northwestern Polytechnical University (Xi'an, China), Waseda University (Kitakyushu, Japan) and Shanghai Jiao Tong University (Shanghai, China).

He holds a PhD in Informatics (Artificial Intelligence - Computer Vision) from the University of Edinburgh and studied Artificial Intelligence and Computer Science as an undergraduate (B.Sc. (Hons.) (Edin.)).

Service and Outreach

Prof. Breckon is a scientific advisor to H.M. Cabinet Office (Cyber Security Expert Group, 2015-present) and previously to H.M. Government Office for Science (2016/17) in areas pertaining to his research specialism.

At Durham, Prof. Breckon led applied Computer Science research, as Head of Innovative Computing within the School of Engineering and Computing Science (2014-2018) and now leads research spanning the visual computing theme as Head of VIViD (Vision, Imaging and Visualisation in Durham, 2021-present) in the Department of Computer Science. From 2020, he serves as a member of the Ethics Advisory Committee bringing broad experience in the application of ethics approval and practice within Artificial Intelligence and related areas.

He is a member of the executive committee of the BMVA (British Machine Vision Association) acting as Treasurer for financial oversight of the association's annual computer vision conferences (BMVC, MIUA), summer school and other activities (2010-present).

In support of outreach, he acts as a STEMNET Science & Engineering Ambassador promoting awareness of intelligent sensing, in terms of both its underpinning technology and related societal impact, and additionally advises the student-led solar challenge race team, Durham University Electric Motorsport (DUEM), on the design of their vehicle telemetry.