mrd45@cam.ac.uk
public key 7B8BF08B
matthew-danish
mrd
mdanishDr Matthew Danish
Founder and consultant at AI Pathfinder.EU.
Visitor at the Computer Laboratory of Cambridge University [former research associate].
[CV]
About
Dr Matthew Danish is an experienced researcher specializing in programming language theory, lightweight verification, machine learning for computer vision, and AI deployment in industrial settings. His work spans operating systems, sensor networks, and object detection on low-power edge devices.
From March to December 2025 he worked at Eindhoven University of Technology's AMOR/e Labs with Klikopmorgen (EDIH), bridging the gap between academia and industry in AI and machine learning. From 2023 to 2025 he was at Utrecht University's Human Geography and Spatial Planning department. Prior to that, he was a postdoctoral research associate at Cambridge University's Computer Science department from 2015 to 2022, working with the Digital Technology Group and Systems Research Group.
At Cambridge from 2015 to 2019, he worked on CamFort and Fortran-Src projects, developing language analysis and refactoring tools for scientific Fortran programs. He collaborated with the Met Office, Bloomberg, and the Numerical Algorithms Group to find bugs in large codebases and modernize legacy programs.
From 2019 to 2022 he was part of the Centre for Digital Built Britain within the Construction Innovation Hub, building intelligent sensors for the West Cambridge Digital Twin project. He developed DeepDish for object detection and tracking on edge systems like Raspberry Pi within the Adaptive City framework, co-authoring papers on intelligent sensors, data management, and complex event recognition.
He served as a volunteer trustee of Cambridge Cycling Campaign (Camcycle) from 2017 to 2022, a local charity with over 1,600 members advocating for safer cycling infrastructure. He led campaigns working with community groups, councillors, and planning officials to create all ages and abilities-friendly cycling infrastructure.
He completed his PhD in Computer Science at Boston University, also while volunteering with local charities and organizations including LivableStreets Alliance, WalkBoston, and Boston Cyclist Union.
Papers, Reports and Presentations
- Danish, M., Labib, SM., Ricker, B., and Helbich, M. A citizen science toolkit to collect human perceptions of urban environments using open street view images. Computers, Environment and Urban Systems. Volume 116, Mar 2025, 102207. [PDF]. arXiv preprint: [PDF]
- Helbich, M., Danish, M., Labib, SM., and Ricker, B. To use or not to use proprietary street view images in (health and place) research? That is the question. Health and Place 87, 2024 [PDF]. arXiv preprint: [PDF]
- Brazauskas, Justas, Chris Jensen, Matthew Danish, Ian Lewis, and Richard Mortier. Cerberus: Privacy-Preserving Crowd Counting and Localisation using Face Detection in Edge Devices. In Proceedings of the 7th International Workshop on Edge Systems, Analytics and Networking, pp. 25-30. 2024. [PDF]
- Matthew Danish, Rohit Verma, Justas Brazauskas, Ian Lewis and Richard Mortier. DeepDish on a diet: low-latency, energy-efficient object-detection and tracking at the edge. In The 5th International Workshop on Edge Systems, Analytics and Networking (EdgeSys), April 2022. [PDF] [Slides]
- Brazauskas, J., Danish, M., Safronov, V., Verma, R., Mortier, R., and Lewis, I. CDBB West Cambridge Digital Twin: Lessons Learned. 2022. arXiv preprint: [PDF]
- Lamb, K., Fenby-Taylor, H., and Danish, M. (2022). Digital Twin Journeys: Teaching a computer to see. Centre for Digital Built Britain. https://doi.org/10.17863/CAM.82150
- Brazauskas, J., Verma, R., Safronov, V., Danish, M., Lewis, I., and Mortier, R. (2021). Real-time data visualisation on the adaptive city platform. In BuildSys 2021 - Proceedings of the 2021 ACM International Conference on Systems for Energy-Efficient Built Environments. [PDF].
- Safronov, Vadim, Justas Brazauskas, Matthew Danish, Rohit Verma, Ian Lewis, and Richard Mortier. Do we want the New Old Internet? Towards Seamless and Protocol-Independent IoT Application Interoperability. In Proceedings of the Twentieth ACM Workshop on Hot Topics in Networks, pp. 185-191. November 2021. [PDF]
- Verma, Rohit, Justas Brazauskas, Vadim Safronov, Matthew Danish, Ian Lewis, and Richard Mortier. RACER: Real-Time Automated Complex Event Recognition in Smart Environments. In Proceedings of the 29th International Conference on Advances in Geographic Information Systems, pp. 634-637. November 2021. [PDF]
- Brazauskas, Justas, Rohit Verma, Vadim Safronov, Matthew Danish, Jorge Merino, Xiang Xie, Ian Lewis, and Richard Mortier. Data Management for Building Information Modelling in a Real-Time Adaptive City Platform. arXiv preprint arXiv:2103.04924. March 2021. [PDF]
- Verma, Rohit, Justas Brazauskas, Vadim Safronov, Matthew Danish, Jorge Merino, Xiang Xie, Ian Lewis, and Richard Mortier. SenseRT: A Streaming Architecture for Smart Building Sensors. arXiv preprint arXiv:2103.09169. March 2021. [PDF]
- Matthew Danish, Justas Brazauskas, Rob Bricheno, Ian Lewis and Richard Mortier. DeepDish: Multi-Object Tracking with an Off-the-Shelf Raspberry Pi. In The 3rd International Workshop on Edge Systems, Analytics and Networking (EdgeSys), April 2020. [PDF] [Slides]
- Orchard, D., Contrastin, M., Danish, M., and Rice, A. (2020). Guiding user annotations for units-of-measure verification. arXiv: [PDF]
- Matthew Danish, Miltiadis Allamanis, Marc Brockschmidt, Andrew Rice and Dominic Orchard. Learning units-of-measure from scientific code. In Software Engineering for Science, May 2019. [PDF]
- Matthew Danish, Dominic Orchard, Andrew Rice. Incremental units-of-measure verification. 2018. arXiv copy (uploaded Jun 2024): [PDF]
- Dominic Orchard, Mistral Contrastin, Matthew Danish, and Andrew Rice. Verifying Spatial Properties of Array Computations. In PACM Progr. Lang. 1, OOPSLA, Article 75. October 2017. [PDF]
- Mistral Contrastin, Andrew Rice, Matthew Danish and Dominic Orchard, Units-of-Measure Correctness in Fortran Programs. In Computing in Science & Engineering, 2016 18(1), Pages 102–107 [web], [preprint]
- Richard West, Ye Li, Eric Missimer, and Matthew Danish. 2016. A Virtualized Separation Kernel for Mixed-Criticality Systems. ACM Trans. Comput. Syst. 34, 3, Article 8 (June 2016), 41 pages. [PDF]
- Matthew Danish, Hongwei Xi. Using lightweight theorem proving in an asynchronous systems context. In Proceedings of the Sixth NASA Formal Methods Symposium. Houston, TX. April 30, 2014. [PDF]
- Matthew Danish. Functional Pearl: Four slot asynchronous communication mechanism. Presented at the ACM SIGPLAN Workshop on Dependently-Typed Programming, informal work-in-progress talk session. Boston, MA. September 24, 2013. [Slides PDF]
- Matthew Danish. Applying Language-based Static Verification in an ARM Operating System. Presented at the High Confidence Software And Systems Conference. May 2013. [Slides PDF]
- Matthew Danish, Hongwei Xi and Richard West. Applying Language-based Static Verification in an ARM Operating System. In Work-in-progress poster session of the 33rd IEEE Real-Time Systems Symposium. San Juan, PR, USA. Dec 4-7, 2012. [PDF]
- Ye Li, Matthew Danish and Richard West. Quest-V: A Virtualized Multikernel for High-Confidence Systems. Technical Report: arXiv:1112.5136, arXiv.org. Also BU Technical Report, 2011-029, Boston University, December 2011. [PDF]
- Matthew Danish, Ye Li and Richard West. Virtual-CPU Scheduling in the Quest Operating System. In Proceedings of the 17th IEEE Real-Time and Embedded Technology and Applications Symposium. Chicago, IL, USA. April 11-14, 2011. [PDF]
- Matthew Danish and Hongwei Xi. Operating System Development with ATS. In PLPV 2010: Proceedings of the 4th Workshop on Programming Languages meets Program Verification. Madrid, Spain. Jan 2010. [PDF]
Geography, Spatial Planning and Computer Vision
Computer Vision, Sensor Networks, Edge Computing and Digital Twins
Static Code Analysis, Scientific Computing and Software Evolution
Dependent Types, Language-based Verification, OS Design and Virtualization
Dissertation
Terrier: An embedded operating system using advanced types for safety. Boston University, 2015. [PDF]Projects
- Percept: toolkit for processing volunteered street view imagery and deploying a perception survey mobile web app
- DeepDish: object recognition and tracking for edge systems
- AdaptiveCity project member (former): real-time urban and in-building sensor data processing
- CamFort project member: lightweight verification, modernisation and analysis tools for computational science models
- Fortran-Src project member: parsing and static analysis for Fortran 66 through 2003
- Terrier: Embedded OS for ARM-based Panda and Beagle Boards.
- Puppy: beginner's framework for a Beagle Board OS
- ATS programming language project member (former)
- Quest operating system project member (former)
Last updated: 30 Apr 2026