Simon Maskell's Homepage

That's me looking rather happy and this is my website. You can contact me on: < s maskell signal qinetiq com>.

I am the "Technical Manager" for ISR (Intelligence, Surveillance and Reconnaissance) Systems and a Senior QinetiQ fellow at QinetiQ and an Hononary Research Fellow in the Communications and Signal Processing Group in the Electrical and Electronic Engineering Department at Imperial College. At QinetiQ, I lead projects conducting research and development (eg into different aspects of the multi-sensor multi-target tracking problem); the algorithms tackle problems such as detection, tracking, optimisation, pattern recognition, information management and intelligence processing.

In 2000, I was lucky enough to be awarded a Royal Commission for the Exhibition of 1851 Industrial Fellowship, which funded my PhD at the Signal Processing Group of Cambridge University Engineering Department. I was supervised by Professor Bill Fitzgerald at Cambridge and by Dr Neil Gordon (who is now at DSTO) and later Dr Alan Marrs at QinetiQ. My thesis was on "Sequentially Structured Bayesian Solutions". I researched how Bayesian tracking algorithms exploit the structure of problem that they tackle: time is ordered and tracking algorithms exploit the fact that knowledge of what's happening now can therefore be sufficient in terms of the past's ability to predict the future. I am now particularly interested in the ability to use the structure of problems in general in the design of algorithms for their solution. As such, I am pleased to be working on difficult problems being tackled by the Artificial Intelligence community for which I hope to develop particularly efficient and robust solutions. These include: inference in graphical models with loops (eg robustly processing very noisy images); learning strategies in partially observed games (ie getting a computer to learn from experience how to fool a human); tracking of articulated objects (eg tracking people in crowds using a network of webcams).

I live very happily with my wife, Michelle, and my two sons in Malvern in Worcestershire, UK; Malvern is about half way between Birmingham and Bristol, so about two hours drive West from London. I thoroughly enjoying playing Rugby fives and occasionally go for a run or play squash, tennis or football. I don't sail though - that's another Simon Maskell. Things I like include: Lobster, Mange Tout, Chocolate, Pink Floyd, Goldie Lookin Chain, The Egg, Fight `Club, Fifth Element, City of Lost Children, Cezanne, Matisse and Picasso. Things I don't like so much include: pickled beetroot, Justin Timberlake, Citizen Kane and Turner.

I went to South America once and took a load of pictures of the Iguazu falls which I merged together. I also went to Marloes Sands in West Wales and Kennedy Space Centre in Florida and did the same. These results look like this:

The following is planned to be an up-to-date list of my publications - time will tell. The publications document my thoughts at various points. Co-authors (who have a mention because they have websites) include Yaakov Bar-Shalom, Mark Briers (who also received one of the aforementioned Royal Commission for the Exhibition of 1851 Industrial Fellowships, to conduct his PhD at Cambridge University with Arnaud Doucet and at QinetiQ with me), Richard Everitt, Kiruba and Ben Alun-Jones. Where possible, I've provided links to versions of the documents.Some of these necessitate appropriate subscriptions to online sources (ieeexplore etc); if the links don't work, it may be because you shouldn't have access!

Journal Papers / Book Chapter

• H Bhaskar, L Mihaylova and S Maskell. Articulated Human Body Parts Detection Based on Cluster Background Subtraction and Foreground Matching. Accepted for publication in Neurocomputing, Special Issue on Behaviours in Video.
• A Gning, L Mihaylova, S Maskell, S Pang and S Godsill. Group Object Structure and State Estimation with Evolving Networks and Monte Carlo Methods. Volume 59, Issue 4, April 2011. pp 1383-1396. IEEE Transactions on Signal Processing.(pdf)
• P Minvielle, A Doucet, A Marrs and S Maskell.A Bayesian Approach to Joint Tracking and Identification of Geometric Shapes in Video Sequences. Journal of Image and Vision Computing. Volume 28, Issue 1, January 2010, Pages 111-123.(pdf)
• M Briers, A Doucet, and S Maskell. Smoothing algorithms for state-space models. Volume 62, Number 1, 61-89. Annals of the Institute of Statistical Mathematics. December 2010.(pdf)
• S Maskell. Statistical Methods for Target Tracking. In Wiley Encyclopedia of Computer Science and Engineering (book). Edited by B W Wah. Published by Hoboken, NJ, January 2009. Vol 5. pp 2820-2829.(pdf)
• S Maskell. A Bayesian Approach to Fusing Uncertain, Imprecise and Conflicting Information. Information Fusion Journal. 9(2):259-277. April 2008.(pdf)
• S Maskell, R Everitt, R Wright and M Briers. Multi-Target Out-of-Sequence Data Association: Tracking Using Graphical Models. Information Fusion Journal, 7(4):434-447. December 2006.(pdf)
• K Hermiston and S Maskell. Fusion Challenges in the Detection and Identification of Difficult Objects and Events. Journal of Defence Science. 10(3), September 2005.
• M Rutten, N Gordon and S Maskell. Recursive Track-Before-Detect with Target Amplitude Fluctuations. IEE Proceedings on Radar Sonar Navigation, 152(5), October 2005, pp345-352 (pdf).
• S Maskell, M Briers, R Wright and P Horridge. Tracking using a Radar and a Problem Specific Proposal Distribution in a Particle Filter. IEE Proceedings on Radar Sonar Navigation, 152(5), October 2005, pp315-322 (pdf).
• S Maskell. Joint Tracking Manoevring Targets and Classification of Their Maneovrability. EURASIP JASP 2004:15 (2004) 2339-2350 (Special Issue of EURASIP Journal on Applied Signal Processing on Particle Filtering in Signal Processing) (pdf).
• S Maskell. Basics of the Particle Filter. In N Shephard and A Harvey, editors, State Space and Unobserved Component Models (book). Cambridge University Press, 2004.
• S Maskell, N Gordon, M Rollason, and D Salmond. Efficient Multitarget Tracking using Particle Filters. Journal Image and Vision Computing, 21(10):931-939, September 2003. (pdf)
• M S Arulampalam, S Maskell, N Gordon, and T Clapp. A Tutorial on Particle Filters for On-line Nonlinear/Non-Gaussian Bayesian Tracking. IEEE Transactions on Signal Processing, 50(2):174-188, February 2002. (pdf)

Conference Papers

• 2011
• P Horridge and S Maskell. Using a Probabilistic Hypothesis Density Filter to Confirm Tracks in a Multi-target Environment.. To appear in Proc SDF 2011.
• 2010
• D Nevell, S Maskell, P Horridge and H Barnett. Fusion of Data Sources with Different Levels of Trust. Proc Fusion 2010.(pdf)
• S Maskell, P Horridge, T Cooper and M Celand. Exchanging Multi-level Maps with Transformations to Support Multi-Modal Alignment. Proc SEAS DTC Conf 2010.(pdf)
• 2009
• S Maskell, P Horridge, D Nevell and T Cooper. Fast Multi-Level Maps and Modelling of Complex Transformations. Proc SEAS DTC Conf 2009.(pdf)
• G Price, V Calloway, S Maskell and K Morgan. Tools and Datapaths to Support Implementation of Divide-and-Conquer Algorithms within an FPGA Vector Co-processor Methodology. Proc EMRS DTC Conf 2009.(pdf)
• P Horridge and S Maskell. A scalable method of tracking targets with dependent distributions. Proc Fusion 2009.(pdf)
• P Horridge and S Maskell. Searching for, initiating and Tracking Multiple Targets Using Existence Probabilities. Proc Fusion 2009.(pdf)
• 2008
• T Cooper and S Maskell. Exchanging Uncertain Multi-Level Maps. In Proc SEAS DTC conference. 2008.(pdf)
• K Morgan and S Maskell. An FPGA Vector Co-Processing Core for Rapid Algorithm Development.In Proc EMRS DTC conference. 2008.(pdf)
• A Gning, L Mihaylova, S Maskell, S K Pang, S Godsill.Ground Target Group Structure and State Estimation with Particle Filtering. Proc. 11th International Conf. on Information Fusion, 2008.(pdf)
• A Gning, L Mihaylova, S Maskell, S K Pang, S Godsill. Evolving Networks for Group Object Motion Estimation. Proc. of the Institution of Engineering and Technology (IET) Seminar on Target Tracking and Data Fusion: Algorithms and Applications, April 2008.(pdf)
• H Bhaskar, L Mihaylova, S Maskell. Population-based Particle Filtering. Proc. of the Institution of Engineering and Technology (IET) Seminar on Target Tracking and Data Fusion: Algorithms and Applications, April 2008.(pdf)
• P Horridge, S Maskell. Tracking with Inter-visibility Variables. Proc. of the Institution of Engineering and Technology (IET) Seminar on Target Tracking and Data Fusion: Algorithms and Applications, April 2008.(pdf)
• J Hill, S Maskell and M Cole. Using Ship Tracking Methods to Assist in Quality Controlling and Bias Adjusting Meteorological Observations in a Marine Environment. Proc. of the Institution of Engineering and Technology (IET) Seminar on Target Tracking and Data Fusion: Algorithms and Applications, April 2008.(pdf)
• H Bhaskar, L Mihaylova, S Maskell. Human Body Parts Tracking Using Pictorial Structures and a Genetic Algorithm. Proc. of the IEEE International Conf. on Intelligent Systems, 6-8 Sept. 2008.(pdf)
• H Bhaskar, L Mihaylova, S Maskell. Multiple Body Part Tracking Using a Probabilistic Data Association Filter. NATO Symposium on "Sensors and Technology for Defence Against Terrorism", 22-25 April, 2008.(pdf)
• 2007
• J Hill, S Maskell, M Cole. Using Ship Tracks to Bias Adjust the Marine Air Temperature Record. Royal Meteorological Society Conference, 2007.(pdf)
• H Bhaskar, L Mihaylova, S Maskell. Automatic Target Detection Based on Background Modeling Using Adaptive Cluster Density Estimation. 3rd German Workshop on Sensor Data Fusion: Trends, Solutions, Applications 2007.(pdf)
• 2006
• S Maskell, B Alun-Jones and M Macleod. A Single Instruction Multiple Data Particle Filter. In Proceedings of Nonlinear Statistical Signal Processing Workshop 2006.(pdf)
• M Strens, J Baxter, M Hernandez, G Moon, S Kapetanakis and S Maskell. Autonomous Decision-Making for Sensor Allocation and Management. Moving Autonomy Forward Conference 2006.
• M Klaas, M Briers, N de Freitas, A Doucet, S Maskell and D Lang. Fast Particle Smoothing: If I Had a Million Particles. ICML 2006. (pdf)
• P Horridge and S Maskell. Real-Time Tracking Of Hundreds Of Targets With Efficient Exact JPDAF Implementation. Proceedings of Fusion 2006.(pdf)
• G Powell, D Marshall, P Smets, B Ristic, S Maskell. Joint Tracking and Classification of Airbourne Objects using Particle Filters and the Continuous Transferable Belief Model. Proceedings of Fusion 2006.(pdf)
• S Maskell, K Weekes and M Briers. Distributed Tracking of Stealthy Targets Using Particle Filters. 2006 IEE Seminar on Target Tracking: Algorithms and Applications.(pdf)
• M Briers, A Doucet, and S Maskell. Fixed-lag Sequential Monte Carlo Data Association. SPIE 2006.(pdf)
• 2005
• K Gilholm, S Godsill, S Maskell, and D Salmond. Poisson models for extended target and group tracking. Proc. SPIE 5913, 59130R (2005). (pdf)
• M Briers, S Maskell, S Reece, S Roberts, I Rezek, VD Dang, A Rogers, NR Jennings. Dynamic sensor coalition formation to assist the distributed tracking of targets: Application to wide-area surveillance. IEE Conference on Homeland Security, 2005. (pdf)
• J Vermaak, S Maskell, M Briers, and P Perez. Bayesian visual tracking with existence process. In proceedings of International Conference Image Processing, 2005.(pdf)
• J Vermaak, S Maskell and M Briers. A Unifying Framework for Multi-Target Tracking and Existence. In proceedings of Fusion 2005.(pdf)
• P Minvielle, A Marrs, S Maskell and A Doucet. Joint Target Tracking and Identification – Part I: Sequential Monte Carlo Model-Based Approaches. In proceedings of Fusion 2005.(pdf).
• P Minvielle, A Marrs, S Maskell and A Doucet. Joint Target Tracking and Identification – Part II: Shape video computing. In proceedings of Fusion 2005.(pdf).
• J Vermaak, S Maskell and M Briers. Online Sensor Registration. In proceedings of IEEE Aerospace Conference, 2005.(pdf)
• JMC Clark, S Maskell, R Vinter and M Yaqoob. A Comparison of the Particle and Shifted Rayleigh Filters in their Application to a Multisensor Bearings-only Problem. In proceedings of IEEE Aerospace Conference, 2005.(pdf)
• 2004
• M Rutten, N Gordon, and S Maskell. Particle-based Track-Before-Detect in Rayleigh Noise. Proceedings of SPIE Conference on Signal Processing of Small Targets, 2004. (pdf)
• M Rutten, S Maskell, M Briers, and N Gordon. Multi-path Track Association for Over-the-Horizon Radar Using Lagrangian Relaxation. Proceedings of SPIE Conference on Signal Processing of Small Targets, 2004. (pdf)
• S Maskell, N Gordon, N Everett, and M Robinson. Tracking Manoeuvring Targets Using a Scale Mixture of Normals. Proceedings of SPIE Conference on Signal Processing of Small Targets, 2004. (pdf)
• S Maskell, M Briers, and R Wright. Fast Mutual Exclusion. Proceedings of SPIE Conference on Signal Processing of Small Targets, 2004. (pdf)
• M Rutten, N Gordon, and S Maskell. Efficient Particle Based Track-Before-Detect in Rayleigh Noise. Proceedings of 7th International Conference on Information Fusion, 2004.(pdf)
• S Maskell, R Everitt, R Wright, and M Briers. Multi-target Out-of-Sequence Data Association. Proceedings of 7th International Conference on Information Fusion, 2004 (pdf).
• S Maskell, M Briers, and R Wright. Tracking Using a Radar and a Problem Specific Proposal Distribution in a Particle Filter. Proceedings of IEE Tracking Conference: Algorithms and Applications, 2004.(pdf)
• 2003
• M Briers, S Maskell, and R Wright. A Rao-Blackwellised Unscented Kalman Filter. In Proceedings of 6th International Conference on Information Fusion, 2003. (pdf)
• M Briers, S Maskell, and M Philpott. Two-dimensional Assignment with Merged Measurements using Lagrangian Relaxation. Proceedings of SPIE Conference on Signal Processing of Small Targets, pages 283-292, 2003.(pdf)
• 2002
• R Wright, S Maskell, M Briers, S Lycett. Robust Tracking of Stealthy Targets and Multi-Sensor Fusion. RAES Classified conference on Data Fusion, 2002.
• A Marrs, S Maskell, and Y Bar-Shalom. Expected Likelihood for Tracking in Clutter with Particle Filters. In O Drummond, editor, Proceedings of SPIE Conference on Signal Processing of Small Targets, pages 230-239, 2002.(pdf)
• S Maskell, N Gordon, M Rollason, and D Salmond. Efficient particle filtering for multiple target tracking with application to tracking in structured images. Proceedings of SPIE Conference on Signal Processing of Small Targets, pages 251-262, 2002.(pdf)
• X Lin, T Kirubarajan, Y Bar-Shalom, S Maskell. Comparison of EKF, Pseudo-measurement Filter and Particle Filter for a Bearings Only Tracking Problem. In Procedings of SPIE: Signal and Data Processing of Small Targets, 2002.(pdf)
• N Gordon, S Maskell, and T Kirubarajan. Efficient Particle Filters for Joint Tracking and Classification. In Procedings of SPIE: Signal and Data Processing of Small Targets, pages 439-449, 2002. (pdf)
• M Hernandez, A Marrs, N Gordon, S Maskell, and C Reed. Cramer-Rao Bounds for Nonlinear Filtering with Measurement Origin Uncertainty. Proceedings of 5th International Conference on Information Fusion, 2002. (pdf)
• M Hernandez, A Marrs, S Maskell, and M Orton. Tracking and Fusion for Wireless Sensor Networks. Proceedings of 5th International Conference on Information Fusion, 2002. (pdf)
• M Mallick, S Maskell, T Kirubarajan, N Gordon. Littoral Tracking using Particle Filter. In Proceedings of Fusion 2002. (pdf)
• S Maskell and N Gordon. A Tutorial on Particle Filters for On-line Nonlinear/Non-Gaussian Bayesian Tracking. In Proceedings of IEE Colloquium on Tracking, 2002 (pdf).

Patent / Thesis / Freely Available (ie not internal to QinetiQ) Technical Reports / Other

• Invited Discussant: C Andrieu, A Doucet, and R Holenstein. Particle Markov chain Monte Carlo methods. Journal of the Royal Statistical Society: Series B (Statistical Methodology). Volume 72, Number 3, pp 269-342, 2010.(pdf)
• General chair for International Conference on Information Fusion 2010, Fusion 2010. (conference website).
• M Briers, A Doucet, and S Maskell. Smoothing Algorithms for State-Space Models. Cambridge University Engineering Department Technical Report, CUED/F-INFENG/TR.498, August 2004. (pdf)
• S Maskell. Signal Processing with Reduced Combinatorial Complexity. July 2003. Patent Reference:0315349.1. A free evaluation licence and associated MATLAB can be obtained by emailing: < ehm signal qinetiq com>.(pdf)
• S Maskell. Sequentially Structured Bayesian Solutions. PhD thesis, Cambridge University Engineering Department, 2004. Chapters can be briefly described as:
  • A review of the tracking literature with a few new extensions.
  • An algorithm for the difficult tracking problem of joint tracking and classification of targets using semi-Markov models.
  • An approach for deriving the models needed for tracking algorithms from SDEs.
  • An efficient (patented) method for exploiting an imposed ordering of multiple targets to improve the efficiency of algorithms such as the JPDAF.
  • A technique for exploiting tracking algorithms in inference in markov meshes and so the analysis of images.
• S Maskell, M Orton, and N Gordon. Efficient Inference for Conditionally Gaussian Markov Random Fields. Technical report, Cambridge University Engineering Department, 2002.
• S Maskell. Multi-Sensor Management. First Year PhD Report. Technical Report, Cambridge University Engineering Department, June 2001.

Fun Stuff

• Red-Riding Hood
• Image Search
• Parkour (aka `Free-running')
• Möbius Gear
• Rob Carter
• Move