Toby Breckon
Head Of Visual Computing at Department for Transport (DfT), United Kingdom
England, United Kingdom
Summary
👤
Senior🎓
Top SchoolToby Breckon is Head of Visual Computing and a Professor in Computer Vision and Image Processing at Durham University, leading an award-winning, industry-facing research group that applies deep learning to real-world sensing and data-understanding challenges. His work has had global impact—helping secure over 500 million air passenger journeys annually and influencing automotive sensing solutions—and has spun out technology adopted by industry players including an Intel-acquired startup. He combines academic leadership (line-managing dozens of researchers and driving ~£1M+/yr research turnover) with government advisory roles on transport and national cyber security risk. A hands-on practitioner as well as a strategist, he contributes to open-source ML projects such as a real-time CNN fire-detection repository that includes model conversions for edge deployment. Trained with a PhD in AI from Edinburgh, he blends deep theoretical expertise with a track record of translating research into deployed systems across continents.
9 years of coding experience
17 years of employment as a software developer
PhD Informatics - Artificial Intelligence (Computer Vision), PhD Informatics - Artificial Intelligence (Computer Vision) at The University of EdinburghPostgraduate Certificate in Higher Eduction (PGCHE) (part-time) Teaching and Learning in Higher Education, Postgraduate Certificate in Higher Eduction (PGCHE) (part-time) Teaching and Learning in Higher Education at Cranfield University
English, French
Github Skills (9)
mask-rcnn10
computer-vision10
faster-rcnn10
tensorflow10
python9
tflite9
opencv9
deep-learning8
machine-learning8
Programming languages (8)
Github contributions (5)
tobybreckon/fire-detection-cnn
Aug 2018 - Sep 2020
real-time fire detection in video imagery using a convolutional neural network (deep learning) - from our ICIP 2018 paper (Dunnings / Breckon) + ICMLA 2019 paper (Samarth / Bhowmik / Breckon)
Role in this project:
ML Engineer
ML EngineerContributions:1 release, 2 reviews, 198 commits in 2 years 2 months
Contributions summary:Toby's commits primarily focus on modifying and improving a convolutional neural network (CNN) for fire detection in video imagery. Their work includes fixing code related to OpenCV versions, refining superpixel processing techniques, and adjusting the network architecture by removing training parameters. They also worked on converting the trained model to .pb and .tflite formats.
pytorchicipdeep-learningdeep-neural-networkconvolutional-neural-network
tobybreckon/cpp-examples-ipcv
Jan 2017 - Jan 2023
C++ Image Processing and Computer Vision OpenCV Examples used for Teaching
Contributions:28 commits, 3 PRs, 22 pushes in 6 years 1 month
cppvisioncomputer-vision-opencvwebcamteaching
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.